N-gram IDF: A Global Term Weighting Scheme Based on Information Distance (WWW...Masumi Shirakawa
A deck of slides for "N-gram IDF: A Global Term Weighting Scheme Based on Information Distance" (Shirakawa et al.) that was presented at 24th International World Wide Web Conference (WWW 2015).
LSGAN - SIMPle(Simple Idea Meaningful Performance Level up)Hansol Kang
LSGAN은 기존의 GAN loss가 아닌 MSE loss를 사용하여, 더욱 realistic한 데이터를 생성함.
LSGAN 논문 리뷰 및 PyTorch 기반의 구현.
[참고]
Mao, Xudong, et al. "Least squares generative adversarial networks." Proceedings of the IEEE International Conference on Computer Vision. 2017.
The document describes Dedalo, a system that automatically explains clusters of data by traversing linked data to find explanations. It evaluates different heuristics for guiding the traversal, finding that entropy and conditional entropy outperform other measures by reducing redundancy and search time. Experiments on authorship clusters, publication clusters, and library book borrowings demonstrate Dedalo's ability to discover explanatory linked data patterns within a limited domain. Future work includes extending Dedalo to handle more complex datasets by addressing issues such as sameAs linking and use of literals.
Joint Word and Entity Embeddings for Entity Retrieval from Knowledge GraphFedorNikolaev
The document proposes a method called KEWER that learns distributed representations of words, entities, and categories from a knowledge graph in the same embedding space. KEWER first generates random walks from entities, replaces some elements with surface forms, and then learns embeddings by maximizing the likelihood of contexts. These embeddings improve entity retrieval over term-based and existing joint embedding models, especially when combined with entity linking.
Selective encoding for abstractive sentence summarizationKodaira Tomonori
This document describes a selective encoding model for abstractive sentence summarization. The model uses a selective gate to filter unimportant information from the encoder states before decoding. It achieves state-of-the-art results on several datasets, outperforming sequence-to-sequence and attention-based models. The model consists of an encoder, selective gate, and decoder. It is trained end-to-end to maximize the likelihood of generating reference summaries.
This document proposes a method to incorporate knowledge graphs (KGs) into neural machine translation (NMT) to improve translation of entities not covered in the training data. It first induces translations of these "K-D entities" by embedding source and target KGs in a unified semantic space. It then generates pseudo sentence pairs containing the induced entity pairs. Finally, it jointly trains the NMT model on the original and pseudo pairs, allowing it to learn mappings for the induced entity translations. Experimental results show the method outperforms baselines, especially on the induced K-D entities.
This document provides information about a GATE CS test paper from 2003 and discusses joining an All India Mock GATE Classroom Test Series conducted by GATE Forum. It includes sample questions from the 2003 GATE CS paper, covering topics like algorithms, data structures, automata theory, databases, computer networks, operating systems and more. 30 questions have one mark each and 60 questions have two marks each. The document encourages visiting the GATE Forum website for more details on joining their test series to help prepare for GATE.
N-gram IDF: A Global Term Weighting Scheme Based on Information Distance (WWW...Masumi Shirakawa
A deck of slides for "N-gram IDF: A Global Term Weighting Scheme Based on Information Distance" (Shirakawa et al.) that was presented at 24th International World Wide Web Conference (WWW 2015).
LSGAN - SIMPle(Simple Idea Meaningful Performance Level up)Hansol Kang
LSGAN은 기존의 GAN loss가 아닌 MSE loss를 사용하여, 더욱 realistic한 데이터를 생성함.
LSGAN 논문 리뷰 및 PyTorch 기반의 구현.
[참고]
Mao, Xudong, et al. "Least squares generative adversarial networks." Proceedings of the IEEE International Conference on Computer Vision. 2017.
The document describes Dedalo, a system that automatically explains clusters of data by traversing linked data to find explanations. It evaluates different heuristics for guiding the traversal, finding that entropy and conditional entropy outperform other measures by reducing redundancy and search time. Experiments on authorship clusters, publication clusters, and library book borrowings demonstrate Dedalo's ability to discover explanatory linked data patterns within a limited domain. Future work includes extending Dedalo to handle more complex datasets by addressing issues such as sameAs linking and use of literals.
Joint Word and Entity Embeddings for Entity Retrieval from Knowledge GraphFedorNikolaev
The document proposes a method called KEWER that learns distributed representations of words, entities, and categories from a knowledge graph in the same embedding space. KEWER first generates random walks from entities, replaces some elements with surface forms, and then learns embeddings by maximizing the likelihood of contexts. These embeddings improve entity retrieval over term-based and existing joint embedding models, especially when combined with entity linking.
Selective encoding for abstractive sentence summarizationKodaira Tomonori
This document describes a selective encoding model for abstractive sentence summarization. The model uses a selective gate to filter unimportant information from the encoder states before decoding. It achieves state-of-the-art results on several datasets, outperforming sequence-to-sequence and attention-based models. The model consists of an encoder, selective gate, and decoder. It is trained end-to-end to maximize the likelihood of generating reference summaries.
This document proposes a method to incorporate knowledge graphs (KGs) into neural machine translation (NMT) to improve translation of entities not covered in the training data. It first induces translations of these "K-D entities" by embedding source and target KGs in a unified semantic space. It then generates pseudo sentence pairs containing the induced entity pairs. Finally, it jointly trains the NMT model on the original and pseudo pairs, allowing it to learn mappings for the induced entity translations. Experimental results show the method outperforms baselines, especially on the induced K-D entities.
This document provides information about a GATE CS test paper from 2003 and discusses joining an All India Mock GATE Classroom Test Series conducted by GATE Forum. It includes sample questions from the 2003 GATE CS paper, covering topics like algorithms, data structures, automata theory, databases, computer networks, operating systems and more. 30 questions have one mark each and 60 questions have two marks each. The document encourages visiting the GATE Forum website for more details on joining their test series to help prepare for GATE.
DCG and NDCG are evaluation measures used to evaluate the performance of ranking models. DCG measures the goodness of a ranking list based on the labels of each document, where documents with higher labels contribute more to the DCG score. NDCG normalizes the DCG score to range from 0 to 1. MAP measures the average precision of a ranking list where labels are binary as relevant or not. Kendall's Tau evaluates how closely the order of items in two lists match on a scale from -1 to 1.
Supplementary material for my following paper: Infinite Latent Process Decomp...Tomonari Masada
This document proposes an infinite latent process decomposition (iLPD) model for microarray data. iLPD extends latent process decomposition (LPD) to allow for an infinite number of latent processes. It presents iLPD's generative process and joint distribution. The document also introduces auxiliary variables and provides a collapsed variational Bayesian inference approach for iLPD. This involves deriving a lower bound for the log evidence to evaluate iLPD's efficiency and compare it to LPD. The proposed method improves on past work by treating full posterior distributions over hyperparameters and removing dependencies in computing the variational lower bound.
Sparse Kernel Learning for Image AnnotationSean Moran
The document describes an approach called Sparse Kernel Continuous Relevance Model (SKL-CRM) for image annotation. SKL-CRM learns data-adaptive visual kernels to better combine different image features like GIST, SIFT, color, and texture. It introduces a binary kernel-feature alignment matrix to learn which kernel functions are best suited to which features by directly optimizing annotation performance on a validation set. Evaluation on standard datasets shows SKL-CRM improves over baselines with fixed 'default' kernels, achieving a relative gain of 10-15% in F1 score.
This document discusses computing commonalities between SPARQL conjunctive queries. It defines the concept of a least general generalization (lgg) of queries, which is a most general query that entails each of the input queries. The document presents definitions for lgg of basic graph pattern queries in SPARQL with respect to a set of RDF entailment rules and RDFS constraints. It focuses on computing the lgg of two queries by iteratively taking the lgg of query pairs. The goal is to study computing lgg in the conjunctive fragment of SPARQL to applications like query optimization and recommendation.
The document describes a new method for optimizing binary tree representations of logic functions to improve throughput. The method aims to reduce logic depth by minimizing delay through grouping Boolean terms with high literal matching. Experimental results on FPGA show the method achieves 10-13% higher maximum throughput and 44-45% lower resource usage compared to an existing method.
Navigating and Exploring RDF Data using Formal Concept AnalysisMehwish Alam
In this study we propose a new approach based on Pattern Structures, an extension of Formal Concept Analysis, to provide exploration over Linked Data through concept lattices. It takes RDF triples and RDF Schema based on user requirements and provides one navigation space resulting from several RDF resources. This navigation space provides interactive exploration over RDF data and allows user to visualize only the part of data that is interesting for her.
PyData Amsterdam - Name Matching at ScaleGoDataDriven
Wendell Kuling works as a Data Scientist at ING in the Wholesale Banking Advanced Analytics team. Their projects aim to provide better services to corporate customers of ING, by using innovative techniques from data-science. In this talk, Wendell covers key insights from their experience in matching large datasets based on names. After covering the key algorithms and packages ING uses for name matching, Wendell will share his best-practice approach in applying these algorithms at scale… would you bet on a Cruncher (48-CPU/512 MB RAM machine), a Tesla (Cuda Tesla K80 with 4992 cores, 24GB memory) or a Spark cluster (80 cores/2,5 TB memory)?
An overview of existing solutions for link discovery and looked into some of the state-of-art algorithms for the rapid execution of link discovery tasks focusing on algorithms which guarantee result completeness.
(HOBBIT project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 688227.)
2P-Kt: logic programming with objects & functions in KotlinGiovanni Ciatto
Mainstream programming languages nowadays tends to be more and more multi-paradigm ones, by integrating diverse programming paradigms -- e.g., object-oriented programming (OOP) and functional programming (FP). Logic-programming (LP) is a successful paradigm that has contributed to many relevant results in the areas of symbolic AI and multi-agent systems, among the others. Whereas Prolog, the most successful LP language, is typically integrated with mainstream languages via foreign language interfaces, in this paper we propose an alternative approach based on the notion of domain-specific language (DSL), which makes LP available to OOP programmers straightforwardly within their OO language of choice. In particular, we present a Kotlin DSL for Prolog, showing how the Kotlin multi-paradigm (OOP + FP) language can be enriched with LP in a straightforward and effective way. Since it is based on the interoperable 2P-Kt project, our technique also enables the creation of similar DSL on top of other high-level languages such as Scala or JavaScript -- thus paving the way towards a more general adoption of LP in general-purpose programming environments.
Looking for Invariant Operators in ArgumentationCarlo Taticchi
We study invariant local expansion operators for conflict-free and admissible sets in Abstract Argumentation Frameworks (AFs). Such operators are directly applied on AFs, and are invariant with respect to a chosen “semantics” (that is w.r.t. each of the conflict free/admissible set of arguments). Accordingly, we derive a definition of robustness for AFs in terms of the number of times such operators can be applied without producing any change in the chosen semantics.
An overview of existing solutions for link discovery and looked into some of the state-of-art algorithms for the rapid execution of link discovery tasks focusing on algorithms which guarantee result completeness.
(HOBBIT project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 688227.)
An overview of existing solutions for link discovery and looked into some of the state-of-art algorithms for the rapid execution of link discovery tasks focusing on algorithms which guarantee result completeness.
(HOBBIT project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 688227.)
Probabilistic Abductive Logic Programming using Possible WorldsFulvio Rotella
Reasoning in very complex contexts often requires purely deductive reasoning to be supported by a variety of techniques that can cope with incomplete data. Abductive inference allows to guess information that has not been explicitly observed. Since there are many explanations for such guesses, there is the need for assigning a probability to each one. This work exploits logical abduction to produce multiple explanations consistent with a given background knowledge and defines a strategy to prioritize them using their chance of being true. Another novelty is the introduction of probabilistic integrity constraints rather than hard ones. Then we propose a strategy that learns model and parameters from data and exploits our Probabilistic Abductive Proof Procedure to classify never-seen instances. This approach has been tested on some standard datasets showing that it improves accuracy in presence of corruptions and missing data.
Learning for semantic parsing using statistical syntactic parsing techniquesUKM university
This document describes Ruifang Ge's Ph.D. final defense presentation on using statistical syntactic parsing techniques for learning semantic parsing. It introduces two novel syntax-based approaches to semantic parsing called SCISSOR and SYNSEM. SCISSOR is an integrated syntactic-semantic parser that allows both syntax and semantics to be used simultaneously to obtain an accurate combined syntactic-semantic analysis. SYNSEM exploits an existing syntactic parser to produce disambiguated parse trees that drive the compositional meaning composition. Experimental results on two datasets show that SCISSOR achieves competitive performance compared to other semantic parsing systems, and that leveraging syntactic knowledge improves performance on longer sentences.
Pascual, Santiago, Antonio Bonafonte, and Joan Serrà. "SEGAN: Speech Enhancement Generative Adversarial Network." INTERSPEECH 2017.
Current speech enhancement techniques operate on the spectral domain and/or exploit some higher-level feature. The majority of them tackle a limited number of noise conditions and rely on first-order statistics. To circumvent these issues, deep networks are being increasingly used, thanks to their ability to learn complex functions from large example sets. In this work, we propose the use of generative adversarial networks for speech enhancement. In contrast to current techniques, we operate at the waveform level, training the model end-to-end, and incorporate 28 speakers and 40 different noise conditions into the same model, such that model parameters are shared across them. We evaluate the proposed model using an independent, unseen test set with two speakers and 20 alternative noise conditions. The enhanced samples confirm the viability of the proposed model, and both objective and subjective evaluations confirm the effectiveness of it. With that, we open the exploration of generative architectures for speech enhancement, which may progressively incorporate further speech-centric design choices to improve their performance.
This document provides an overview of hands-on tasks for a link discovery tutorial using the Limes framework. It describes a test dataset, and three tasks: 1) executing a provided Limes configuration to detect duplicate authors, 2) creating a configuration to find similar publications based on keywords, and 3) using the Limes GUI.
A lexisearch algorithm for the Bottleneck Traveling Salesman ProblemCSCJournals
The Bottleneck Traveling Salesman Problem (BTSP) is a variation of the well-known Traveling Salesman Problem in which the objective is to minimize the maximum lap (arc length) in the tour of the salesman. In this paper, a lexisearch algorithm using adjacency representation for a tour has been developed for obtaining exact optimal solution to the problem. Then a comparative study has been carried out to show the efficiency of the algorithm as against existing exact algorithm for some randomly generated and TSPLIB instances of different sizes.
The document discusses extending OWL with integrity constraints. It notes that while OWL uses the open world assumption (OWA) and non-unique name assumption (nUNA), there is a strong need to use OWL as an integrity constraint language, especially in hybrid settings. It reviews related work on rule-based, epistemic query-based, and epistemic description logic approaches and their limitations. The authors propose an approach that reuses OWL as the integrity constraint language.
This document discusses knowledge discovery and machine learning on graph data. It makes three main observations:
1) Graphs are typically constructed from input data rather than given directly, as relationships must be inferred.
2) Graph data management is challenging due to issues like large size, dynamic nature, heterogeneity and attribution.
3) Useful insights and accurate modeling depend on the representation of the data as a graph, such as through decomposition, feature learning or other techniques.
On the value of Sampling and Pruning for SBSEJianfeng Chen
Oral Prelim Exam slides (for publication).
Thesis statement: for the optimization of SE planning and replanning tasks, given appropriate separation operators, then oversampling and pruning is better than mutation based evolutionary approaches.
DCG and NDCG are evaluation measures used to evaluate the performance of ranking models. DCG measures the goodness of a ranking list based on the labels of each document, where documents with higher labels contribute more to the DCG score. NDCG normalizes the DCG score to range from 0 to 1. MAP measures the average precision of a ranking list where labels are binary as relevant or not. Kendall's Tau evaluates how closely the order of items in two lists match on a scale from -1 to 1.
Supplementary material for my following paper: Infinite Latent Process Decomp...Tomonari Masada
This document proposes an infinite latent process decomposition (iLPD) model for microarray data. iLPD extends latent process decomposition (LPD) to allow for an infinite number of latent processes. It presents iLPD's generative process and joint distribution. The document also introduces auxiliary variables and provides a collapsed variational Bayesian inference approach for iLPD. This involves deriving a lower bound for the log evidence to evaluate iLPD's efficiency and compare it to LPD. The proposed method improves on past work by treating full posterior distributions over hyperparameters and removing dependencies in computing the variational lower bound.
Sparse Kernel Learning for Image AnnotationSean Moran
The document describes an approach called Sparse Kernel Continuous Relevance Model (SKL-CRM) for image annotation. SKL-CRM learns data-adaptive visual kernels to better combine different image features like GIST, SIFT, color, and texture. It introduces a binary kernel-feature alignment matrix to learn which kernel functions are best suited to which features by directly optimizing annotation performance on a validation set. Evaluation on standard datasets shows SKL-CRM improves over baselines with fixed 'default' kernels, achieving a relative gain of 10-15% in F1 score.
This document discusses computing commonalities between SPARQL conjunctive queries. It defines the concept of a least general generalization (lgg) of queries, which is a most general query that entails each of the input queries. The document presents definitions for lgg of basic graph pattern queries in SPARQL with respect to a set of RDF entailment rules and RDFS constraints. It focuses on computing the lgg of two queries by iteratively taking the lgg of query pairs. The goal is to study computing lgg in the conjunctive fragment of SPARQL to applications like query optimization and recommendation.
The document describes a new method for optimizing binary tree representations of logic functions to improve throughput. The method aims to reduce logic depth by minimizing delay through grouping Boolean terms with high literal matching. Experimental results on FPGA show the method achieves 10-13% higher maximum throughput and 44-45% lower resource usage compared to an existing method.
Navigating and Exploring RDF Data using Formal Concept AnalysisMehwish Alam
In this study we propose a new approach based on Pattern Structures, an extension of Formal Concept Analysis, to provide exploration over Linked Data through concept lattices. It takes RDF triples and RDF Schema based on user requirements and provides one navigation space resulting from several RDF resources. This navigation space provides interactive exploration over RDF data and allows user to visualize only the part of data that is interesting for her.
PyData Amsterdam - Name Matching at ScaleGoDataDriven
Wendell Kuling works as a Data Scientist at ING in the Wholesale Banking Advanced Analytics team. Their projects aim to provide better services to corporate customers of ING, by using innovative techniques from data-science. In this talk, Wendell covers key insights from their experience in matching large datasets based on names. After covering the key algorithms and packages ING uses for name matching, Wendell will share his best-practice approach in applying these algorithms at scale… would you bet on a Cruncher (48-CPU/512 MB RAM machine), a Tesla (Cuda Tesla K80 with 4992 cores, 24GB memory) or a Spark cluster (80 cores/2,5 TB memory)?
An overview of existing solutions for link discovery and looked into some of the state-of-art algorithms for the rapid execution of link discovery tasks focusing on algorithms which guarantee result completeness.
(HOBBIT project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 688227.)
2P-Kt: logic programming with objects & functions in KotlinGiovanni Ciatto
Mainstream programming languages nowadays tends to be more and more multi-paradigm ones, by integrating diverse programming paradigms -- e.g., object-oriented programming (OOP) and functional programming (FP). Logic-programming (LP) is a successful paradigm that has contributed to many relevant results in the areas of symbolic AI and multi-agent systems, among the others. Whereas Prolog, the most successful LP language, is typically integrated with mainstream languages via foreign language interfaces, in this paper we propose an alternative approach based on the notion of domain-specific language (DSL), which makes LP available to OOP programmers straightforwardly within their OO language of choice. In particular, we present a Kotlin DSL for Prolog, showing how the Kotlin multi-paradigm (OOP + FP) language can be enriched with LP in a straightforward and effective way. Since it is based on the interoperable 2P-Kt project, our technique also enables the creation of similar DSL on top of other high-level languages such as Scala or JavaScript -- thus paving the way towards a more general adoption of LP in general-purpose programming environments.
Looking for Invariant Operators in ArgumentationCarlo Taticchi
We study invariant local expansion operators for conflict-free and admissible sets in Abstract Argumentation Frameworks (AFs). Such operators are directly applied on AFs, and are invariant with respect to a chosen “semantics” (that is w.r.t. each of the conflict free/admissible set of arguments). Accordingly, we derive a definition of robustness for AFs in terms of the number of times such operators can be applied without producing any change in the chosen semantics.
An overview of existing solutions for link discovery and looked into some of the state-of-art algorithms for the rapid execution of link discovery tasks focusing on algorithms which guarantee result completeness.
(HOBBIT project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 688227.)
An overview of existing solutions for link discovery and looked into some of the state-of-art algorithms for the rapid execution of link discovery tasks focusing on algorithms which guarantee result completeness.
(HOBBIT project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 688227.)
Probabilistic Abductive Logic Programming using Possible WorldsFulvio Rotella
Reasoning in very complex contexts often requires purely deductive reasoning to be supported by a variety of techniques that can cope with incomplete data. Abductive inference allows to guess information that has not been explicitly observed. Since there are many explanations for such guesses, there is the need for assigning a probability to each one. This work exploits logical abduction to produce multiple explanations consistent with a given background knowledge and defines a strategy to prioritize them using their chance of being true. Another novelty is the introduction of probabilistic integrity constraints rather than hard ones. Then we propose a strategy that learns model and parameters from data and exploits our Probabilistic Abductive Proof Procedure to classify never-seen instances. This approach has been tested on some standard datasets showing that it improves accuracy in presence of corruptions and missing data.
Learning for semantic parsing using statistical syntactic parsing techniquesUKM university
This document describes Ruifang Ge's Ph.D. final defense presentation on using statistical syntactic parsing techniques for learning semantic parsing. It introduces two novel syntax-based approaches to semantic parsing called SCISSOR and SYNSEM. SCISSOR is an integrated syntactic-semantic parser that allows both syntax and semantics to be used simultaneously to obtain an accurate combined syntactic-semantic analysis. SYNSEM exploits an existing syntactic parser to produce disambiguated parse trees that drive the compositional meaning composition. Experimental results on two datasets show that SCISSOR achieves competitive performance compared to other semantic parsing systems, and that leveraging syntactic knowledge improves performance on longer sentences.
Pascual, Santiago, Antonio Bonafonte, and Joan Serrà. "SEGAN: Speech Enhancement Generative Adversarial Network." INTERSPEECH 2017.
Current speech enhancement techniques operate on the spectral domain and/or exploit some higher-level feature. The majority of them tackle a limited number of noise conditions and rely on first-order statistics. To circumvent these issues, deep networks are being increasingly used, thanks to their ability to learn complex functions from large example sets. In this work, we propose the use of generative adversarial networks for speech enhancement. In contrast to current techniques, we operate at the waveform level, training the model end-to-end, and incorporate 28 speakers and 40 different noise conditions into the same model, such that model parameters are shared across them. We evaluate the proposed model using an independent, unseen test set with two speakers and 20 alternative noise conditions. The enhanced samples confirm the viability of the proposed model, and both objective and subjective evaluations confirm the effectiveness of it. With that, we open the exploration of generative architectures for speech enhancement, which may progressively incorporate further speech-centric design choices to improve their performance.
This document provides an overview of hands-on tasks for a link discovery tutorial using the Limes framework. It describes a test dataset, and three tasks: 1) executing a provided Limes configuration to detect duplicate authors, 2) creating a configuration to find similar publications based on keywords, and 3) using the Limes GUI.
A lexisearch algorithm for the Bottleneck Traveling Salesman ProblemCSCJournals
The Bottleneck Traveling Salesman Problem (BTSP) is a variation of the well-known Traveling Salesman Problem in which the objective is to minimize the maximum lap (arc length) in the tour of the salesman. In this paper, a lexisearch algorithm using adjacency representation for a tour has been developed for obtaining exact optimal solution to the problem. Then a comparative study has been carried out to show the efficiency of the algorithm as against existing exact algorithm for some randomly generated and TSPLIB instances of different sizes.
The document discusses extending OWL with integrity constraints. It notes that while OWL uses the open world assumption (OWA) and non-unique name assumption (nUNA), there is a strong need to use OWL as an integrity constraint language, especially in hybrid settings. It reviews related work on rule-based, epistemic query-based, and epistemic description logic approaches and their limitations. The authors propose an approach that reuses OWL as the integrity constraint language.
This document discusses knowledge discovery and machine learning on graph data. It makes three main observations:
1) Graphs are typically constructed from input data rather than given directly, as relationships must be inferred.
2) Graph data management is challenging due to issues like large size, dynamic nature, heterogeneity and attribution.
3) Useful insights and accurate modeling depend on the representation of the data as a graph, such as through decomposition, feature learning or other techniques.
On the value of Sampling and Pruning for SBSEJianfeng Chen
Oral Prelim Exam slides (for publication).
Thesis statement: for the optimization of SE planning and replanning tasks, given appropriate separation operators, then oversampling and pruning is better than mutation based evolutionary approaches.
How can we apply machine learning techniques on graphs to obtain predictions in a variety of domains? Know more from Sami Abu-El-Haija, an AI Scientist with experience from both industry (Google Research) and academia (University of Southern California).
The document describes algorithms for solving the union-find problem, which involves maintaining disjoint sets under union and find operations. It introduces the quick-find, quick-union, and weighted quick-union algorithms. Quick-find is too slow for union operations, which can require quadratic time. Quick-union improves on this but find operations can be slow. Weighted quick-union balances trees during union to keep depths logarithmic, improving performance of both operations.
The document describes algorithms for solving the union-find problem, which involves maintaining disjoint sets under union and find operations. It introduces the quick-find, quick-union, and weighted quick-union algorithms. Quick-find is too slow for union operations, which can require quadratic time. Quick-union improves on this but find operations can be slow. Weighted quick-union balances trees during union to keep depths logarithmic, improving performance of both operations.
DiscoGAN - Learning to Discover Cross-Domain Relations with Generative Advers...Taeksoo Kim
The document describes DiscoGAN, a method for discovering cross-domain relations between images using generative adversarial networks (GANs) without paired datasets. DiscoGAN uses two GANs, with each GAN consisting of a generator and discriminator, to learn translation functions between domains in both directions. It adds reconstruction losses to enforce cycle consistency. Experimental results show DiscoGAN can translate between domains like rotating cars, male to female faces, cars to faces, and handbags to shoes. The conclusion summarizes that DiscoGAN allows learning cross-domain relations between very different datasets without explicit pair labels.
A Study of the Similarities of Entity Embeddings Learned from Different Aspec...GUANGYUAN PIAO
This study examines the similarities between entity embeddings learned from different aspects of a knowledge base for item recommendations. The researchers used music and book datasets to learn embeddings from the knowledge base's homogeneous graph structure, textual descriptions, and heterogeneous entity-relation graph. Evaluating the embeddings using recommendation metrics showed that embeddings from the homogeneous graph performed best, and combining embeddings from the heterogeneous graph and text outperformed using each source individually. The researchers propose exploring other embedding techniques and better utilizing domain-specific knowledge.
Syntactic Mediation in Grid and Web Service ArchitecturesMartin Szomszor
The document discusses syntactic mediation between services in grid and web service architectures. Syntactic mediation is required when the output of one service is not compatible with the input of another service due to different data formats, even if they represent the same conceptual data. The document proposes using ontologies and mappings between data schemas and ontologies to transform between different syntactic representations and allow services to interoperate. Mappings are described in a simple language and used by a mapping engine to transform between XML and OWL representations. This approach allows assisted mediation between incompatible services.
The document is a training report submitted by Navneet Kumar for the completion of a Data Structures and Algorithms (DSA) self-paced course from June 2023 to August 2023. It includes declarations by the student, acknowledgements, a table of contents, and sections on the technologies learned including data structures, algorithms, mathematics, and programming concepts. The student learned topics from basic to advanced levels including arrays, strings, linked lists, stacks, queues, trees, graphs, sorting, searching, hashing and more. The goal was to improve problem solving and analytical skills for software developer interviews.
Chaos Testing with F# and Azure by Rachel Reese at Codemotion DubaiCodemotion Dubai
Some of the biggest growing pains we've experienced with our microservice architecture at Jet is in preparing for system outages. I'll cover the benefits of choosing F# specifically, and functional programming in general, as well as Azure, for a chaos program. I'll follow up with a discussion of why your team needs to implement a chaos testing program, and finish with showing off our methods and code in depth.
All About GRAND Stack: GraphQL, React, Apollo, and Neo4j (Mark Needham) - Gre...GreeceJS
In this presentation, we explore application development using the GRAND stack (GraphQL, React, Apollo, Neo4j) for building web applications backed by a graph database. We will review the components to build a simple web application, including how to build a React component, an introduction to JSX, an overview of GraphQL and why it is a game-changer for front-end development. We'll learn how to model, store, and query data in the Neo4j graph database using GraphQL to power our web application.
The document discusses optimizing the performance of Word2Vec on multicore systems through a technique called Context Combining. Some key points:
- Context Combining improves Word2Vec training efficiency by combining related windows that share samples, improving floating point throughput and reducing overhead.
- Experiments on Intel and Intel Knights Landing processors show Context Combining (pSGNScc) achieves up to 1.28x speedup over prior work (pWord2Vec) and maintains comparable accuracy to state-of-the-art implementations.
- Parallel scaling tests show pSGNScc achieves near linear speedup up to 68 cores, utilizing more of the available computational resources than previous techniques.
- Future
Bootstrapping Entity Alignment with Knowledge Graph EmbeddingNanjing University
This document presents BootEA, a framework for bootstrapping entity alignment across knowledge graphs using knowledge graph embedding. BootEA models entity alignment as a classification task and trains alignment-oriented knowledge graph embeddings using an iterative process of parameter swapping, alignment prediction, labeling likely alignments, and editing alignments. Experimental results on five datasets show that BootEA significantly outperforms three state-of-the-art embedding-based entity alignment methods, particularly on sparse data.
5th in the AskTOM Office Hours series on graph database technologies. https://devgym.oracle.com/pls/apex/dg/office_hours/3084
PGQL: A Query Language for Graphs
Learn how to query graphs using PGQL, an expressive and intuitive graph query language that's a lot like SQL. With PGQL, it's easy to get going writing graph analysis queries to the database in a very short time. Albert and Oskar show what you can do with PGQL, and how to write and execute PGQL code.
Co-Learning: Consensus-based Learning for Multi-Agent SystemsMiguel Rebollo
Distributed federated learning using consensus with intelligent agents over a network. Work presented to the 20th International Conference on Practical Applications of Agents and Multi-Agent Systems. July 2022 L'Aquila (Italy)
This document discusses recent developments in AI, including large language models like ChatGPT, interaction-centric AI, efficient information retrieval techniques, and approximate nearest neighbor search. Specific papers and techniques summarized include TART for task-aware retrieval with instructions, CITADEL for multi-vector retrieval using dynamic lexical routing, OOD-DiskANN for out-of-distribution queries in ANN search, and improvements to ANN search through techniques like robust graph optimization and query-aware product quantization. The document promotes Weaviate as a vector search engine and encourages feedback on interesting parts.
Presentation of the Conference paper: "Empirical Analysis of IPv6 Transition Technologies Using the IPv6 Network Evaluation Testbed" in Tridentcom 2014, Guangzhou , China
The document discusses various incremental improvements made to the Java platform between major Java releases from JDK 9 to JDK 12. Some key improvements discussed include adding support for array mismatch and lexicographical comparison in JDK 9, enhancing performance of comparison and mismatching over nio Buffers in JDK 11, adding the ability to execute Java source without compilation in JDK 11, introducing collection literals in JDK 9, and various HotSpot enhancements like fused multiply and add vectorization and square root vectorization of floats in JDK 10 and 11.
Labeled generalized stochastic petri net Based approach for web services Comp...ijcsit
This document proposes an approach for modeling and composing web services using Labeled Generalized Stochastic Petri Nets (LGSPNs). LGSPNs are presented as an expressive way to formally model both the structure and behavior of individual web services. An algebra is then defined to compose existing web services modeled as LGSPNs in order to create new composite services. The composition operators allow incrementally building more complex services through the combination of basic services. The LGSPN modeling approach is argued to provide benefits for understanding, analyzing, and prototyping complex web service compositions.
Similar to Encoding Linguistic Structures with Graph Convolutional Networks (20)
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2024/06/building-and-scaling-ai-applications-with-the-nx-ai-manager-a-presentation-from-network-optix/
Robin van Emden, Senior Director of Data Science at Network Optix, presents the “Building and Scaling AI Applications with the Nx AI Manager,” tutorial at the May 2024 Embedded Vision Summit.
In this presentation, van Emden covers the basics of scaling edge AI solutions using the Nx tool kit. He emphasizes the process of developing AI models and deploying them globally. He also showcases the conversion of AI models and the creation of effective edge AI pipelines, with a focus on pre-processing, model conversion, selecting the appropriate inference engine for the target hardware and post-processing.
van Emden shows how Nx can simplify the developer’s life and facilitate a rapid transition from concept to production-ready applications.He provides valuable insights into developing scalable and efficient edge AI solutions, with a strong focus on practical implementation.
Infrastructure Challenges in Scaling RAG with Custom AI modelsZilliz
Building Retrieval-Augmented Generation (RAG) systems with open-source and custom AI models is a complex task. This talk explores the challenges in productionizing RAG systems, including retrieval performance, response synthesis, and evaluation. We’ll discuss how to leverage open-source models like text embeddings, language models, and custom fine-tuned models to enhance RAG performance. Additionally, we’ll cover how BentoML can help orchestrate and scale these AI components efficiently, ensuring seamless deployment and management of RAG systems in the cloud.
Threats to mobile devices are more prevalent and increasing in scope and complexity. Users of mobile devices desire to take full advantage of the features
available on those devices, but many of the features provide convenience and capability but sacrifice security. This best practices guide outlines steps the users can take to better protect personal devices and information.
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slackshyamraj55
Discover the seamless integration of RPA (Robotic Process Automation), COMPOSER, and APM with AWS IDP enhanced with Slack notifications. Explore how these technologies converge to streamline workflows, optimize performance, and ensure secure access, all while leveraging the power of AWS IDP and real-time communication via Slack notifications.
Taking AI to the Next Level in Manufacturing.pdfssuserfac0301
Read Taking AI to the Next Level in Manufacturing to gain insights on AI adoption in the manufacturing industry, such as:
1. How quickly AI is being implemented in manufacturing.
2. Which barriers stand in the way of AI adoption.
3. How data quality and governance form the backbone of AI.
4. Organizational processes and structures that may inhibit effective AI adoption.
6. Ideas and approaches to help build your organization's AI strategy.
“An Outlook of the Ongoing and Future Relationship between Blockchain Technologies and Process-aware Information Systems.” Invited talk at the joint workshop on Blockchain for Information Systems (BC4IS) and Blockchain for Trusted Data Sharing (B4TDS), co-located with with the 36th International Conference on Advanced Information Systems Engineering (CAiSE), 3 June 2024, Limassol, Cyprus.
TrustArc Webinar - 2024 Global Privacy SurveyTrustArc
How does your privacy program stack up against your peers? What challenges are privacy teams tackling and prioritizing in 2024?
In the fifth annual Global Privacy Benchmarks Survey, we asked over 1,800 global privacy professionals and business executives to share their perspectives on the current state of privacy inside and outside of their organizations. This year’s report focused on emerging areas of importance for privacy and compliance professionals, including considerations and implications of Artificial Intelligence (AI) technologies, building brand trust, and different approaches for achieving higher privacy competence scores.
See how organizational priorities and strategic approaches to data security and privacy are evolving around the globe.
This webinar will review:
- The top 10 privacy insights from the fifth annual Global Privacy Benchmarks Survey
- The top challenges for privacy leaders, practitioners, and organizations in 2024
- Key themes to consider in developing and maintaining your privacy program
OpenID AuthZEN Interop Read Out - AuthorizationDavid Brossard
During Identiverse 2024 and EIC 2024, members of the OpenID AuthZEN WG got together and demoed their authorization endpoints conforming to the AuthZEN API
AI 101: An Introduction to the Basics and Impact of Artificial IntelligenceIndexBug
Imagine a world where machines not only perform tasks but also learn, adapt, and make decisions. This is the promise of Artificial Intelligence (AI), a technology that's not just enhancing our lives but revolutionizing entire industries.
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfMalak Abu Hammad
Discover how MongoDB Atlas and vector search technology can revolutionize your application's search capabilities. This comprehensive presentation covers:
* What is Vector Search?
* Importance and benefits of vector search
* Practical use cases across various industries
* Step-by-step implementation guide
* Live demos with code snippets
* Enhancing LLM capabilities with vector search
* Best practices and optimization strategies
Perfect for developers, AI enthusiasts, and tech leaders. Learn how to leverage MongoDB Atlas to deliver highly relevant, context-aware search results, transforming your data retrieval process. Stay ahead in tech innovation and maximize the potential of your applications.
#MongoDB #VectorSearch #AI #SemanticSearch #TechInnovation #DataScience #LLM #MachineLearning #SearchTechnology
Full-RAG: A modern architecture for hyper-personalizationZilliz
Mike Del Balso, CEO & Co-Founder at Tecton, presents "Full RAG," a novel approach to AI recommendation systems, aiming to push beyond the limitations of traditional models through a deep integration of contextual insights and real-time data, leveraging the Retrieval-Augmented Generation architecture. This talk will outline Full RAG's potential to significantly enhance personalization, address engineering challenges such as data management and model training, and introduce data enrichment with reranking as a key solution. Attendees will gain crucial insights into the importance of hyperpersonalization in AI, the capabilities of Full RAG for advanced personalization, and strategies for managing complex data integrations for deploying cutting-edge AI solutions.
CAKE: Sharing Slices of Confidential Data on BlockchainClaudio Di Ciccio
Presented at the CAiSE 2024 Forum, Intelligent Information Systems, June 6th, Limassol, Cyprus.
Synopsis: Cooperative information systems typically involve various entities in a collaborative process within a distributed environment. Blockchain technology offers a mechanism for automating such processes, even when only partial trust exists among participants. The data stored on the blockchain is replicated across all nodes in the network, ensuring accessibility to all participants. While this aspect facilitates traceability, integrity, and persistence, it poses challenges for adopting public blockchains in enterprise settings due to confidentiality issues. In this paper, we present a software tool named Control Access via Key Encryption (CAKE), designed to ensure data confidentiality in scenarios involving public blockchains. After outlining its core components and functionalities, we showcase the application of CAKE in the context of a real-world cyber-security project within the logistics domain.
Paper: https://doi.org/10.1007/978-3-031-61000-4_16
Essentials of Automations: The Art of Triggers and Actions in FMESafe Software
In this second installment of our Essentials of Automations webinar series, we’ll explore the landscape of triggers and actions, guiding you through the nuances of authoring and adapting workspaces for seamless automations. Gain an understanding of the full spectrum of triggers and actions available in FME, empowering you to enhance your workspaces for efficient automation.
We’ll kick things off by showcasing the most commonly used event-based triggers, introducing you to various automation workflows like manual triggers, schedules, directory watchers, and more. Plus, see how these elements play out in real scenarios.
Whether you’re tweaking your current setup or building from the ground up, this session will arm you with the tools and insights needed to transform your FME usage into a powerhouse of productivity. Join us to discover effective strategies that simplify complex processes, enhancing your productivity and transforming your data management practices with FME. Let’s turn complexity into clarity and make your workspaces work wonders!
GraphRAG for Life Science to increase LLM accuracyTomaz Bratanic
GraphRAG for life science domain, where you retriever information from biomedical knowledge graphs using LLMs to increase the accuracy and performance of generated answers
Have you ever been confused by the myriad of choices offered by AWS for hosting a website or an API?
Lambda, Elastic Beanstalk, Lightsail, Amplify, S3 (and more!) can each host websites + APIs. But which one should we choose?
Which one is cheapest? Which one is fastest? Which one will scale to meet our needs?
Join me in this session as we dive into each AWS hosting service to determine which one is best for your scenario and explain why!
AI-Powered Food Delivery Transforming App Development in Saudi Arabia.pdfTechgropse Pvt.Ltd.
In this blog post, we'll delve into the intersection of AI and app development in Saudi Arabia, focusing on the food delivery sector. We'll explore how AI is revolutionizing the way Saudi consumers order food, how restaurants manage their operations, and how delivery partners navigate the bustling streets of cities like Riyadh, Jeddah, and Dammam. Through real-world case studies, we'll showcase how leading Saudi food delivery apps are leveraging AI to redefine convenience, personalization, and efficiency.
Unlocking Productivity: Leveraging the Potential of Copilot in Microsoft 365, a presentation by Christoforos Vlachos, Senior Solutions Manager – Modern Workplace, Uni Systems
Encoding Linguistic Structures with Graph Convolutional Networks
1. Encoding Linguistic Structures with
Graph Convolutional Networks
Diego Marcheggiani
Joint work with IvanTitov and Joost Bastings
University of Amsterdam
University of Edinburgh
@South England NLP Meetup
2. Structured (Linguistic) Priors
Sequa makes and repairs jet engines.
creator
creation
entity repaired
repairer
SBJ COORD
OBJ
CONJ NMOD
ROOT
“I voted for Palpatine because he was
most aligned with my values,” she said.
2
4. Sequence to Sequence
} Language is not (only) a sequence of words
} We have linguistic knowledge
4
[Sutskever et al., 2014]
the black cat
le chat noire <s>
<s> le chat noire
5. Sequence to Sequence
} Language is not (only) a sequence of words
} We have linguistic knowledge
Encode structured linguistic knowledge into NN using
Graph Convolutional Networks
5
the black cat
le chat noire <s>
<s> le chat noire
6. Outline
} Semantic Role Labeling
} Graph Convolutional Networks (GCN)
} Syntactic GCN for Semantic Role Labeling (SRL)
} SRL Model
} Exploiting Semantics in Neural MachineTranslation with GCNs
Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling
Diego Marcheggiani,IvanTitov. In Proceedings of EMNLP, 2017.
Exploiting Semantics in Neural MachineTranslation with Graph Convolutional Networks
Diego Marcheggiani,Joost Bastings,IvanTitov. In Proceedings of NAACL-HLT, 2018.
6
7. Semantic Role Labeling
} Predicting the predicate-argument structure of a sentence
Sequa makes and repairs jet engines.
Sequa makes and repairs jet engines.
7
8. Semantic Role Labeling
} Predicting the predicate-argument structure of a sentence
} Discover and disambiguate predicates
8
Sequa makes and repairs jet engines.
make.01 repair.01
Sequa makes and repairs jet engines.
9. } Predicting the predicate-argument structure of a sentence
} Discover and disambiguate predicates
} Identify arguments and label them with their semantic roles
Sequa makes and repairs jet engines.
make.01 repair.01
Creator
Semantic Role Labeling
9
10. } Predicting the predicate-argument structure of a sentence
} Discover and disambiguate predicates
} Identify arguments and label them with their semantic roles
Sequa makes and repairs jet engines.
make.01 repair.01
Creator
Creation
Semantic Role Labeling
10
11. } Predicting the predicate-argument structure of a sentence
} Discover and disambiguate predicates
} Identify arguments and label them with their semantic roles
Sequa makes and repairs jet engines.
make.01 repair.01
Creator
Creation
Entity repaired
Repairer
Semantic Role Labeling
11
12. Semantic Role Labeling
} Only the head of an argument is labeled
} Sequence labeling task for each predicate
} Focus on argument identification and labeling
12
Sequa makes and repairs jet engines.
make.01 repair.01
Creator
Creation
Entity repaired
Repairer
13. Semantic Role Labeling
13
Question answering
Narayanan and Harabagiu 2004
Shen and Lapata 2007
Khashabi et al. 2018
Machine translation
Wu and Fung 2009
Aziz et al. 2011
Information extraction
Surdeanu et al. 2003
Christensen et al. 2010
15. Related work
} SRL systems that use syntax with simple NN architectures
} [FitzGerald et al., 2015]
} [Roth and Lapata,2016]
} Recent models ignore linguistic bias
} [Zhou and Xu, 2014]
} [He et al., 2017]
} [Marcheggiani et al., 2017]
15
Tutorial on Semantic Role
Labeling at EMNLP 2017
16. Motivations
} Some semantic dependencies are mirrored in the syntactic graph
Sequa makes and repairs jet engines.
creator
creation
SBJ COORD
OBJ
CONJ NMOD
ROOT
16
17. Sequa makes and repairs jet engines.
creator
creation
entity repaired
repairer
SBJ COORD
OBJ
CONJ NMOD
ROOT
Motivations
} Some semantic dependencies are mirrored in the syntactic graph
} Not all of them – syntax-semantics interface is not trivial
17
18. Outline
} Semantic Role Labeling
} Graph Convolutional Networks (GCN)
} Syntactic GCN for Semantic Role Labeling (SRL)
} SRL Model
} Exploiting Semantics in Neural MachineTranslation with GCNs
18
19. Graph Convolutional Networks (message passing)
Undirected graph
[Gori et al. 2005
Scarselli et al. 2009
Kipf and Welling,2016]
19
20. Graph Convolutional Networks (message passing)
Undirected graph Update of the blue node
[Gori et al. 2005
Scarselli et al. 2009
Kipf and Welling,2016]
20
21. Graph Convolutional Networks (message passing)
Undirected graph Update of the blue node
[Kipf and Welling,2016]
21
hi = ReLU
0
@W0hi +
X
j2N (v)
W1hj
1
A
<latexit sha1_base64="dRNZOAdr3+64yfJmCNqaHzngt30=">AAACcXicbVFdS9xAFJ2kttqtrdv6VEQYXGxXhCWRQvtSkPbFBxEt3Q8wS5jM3mxGJ5MwcyMNIT/Cn9Wf0N/Rh746WaOwbi8MnDnn3LkfE+VSGPS8P477bO35i/WNl51Xm6/fbHXfvhuZrNAchjyTmZ5EzIAUCoYoUMIk18DSSMI4uv7e6OMb0EZk6ieWOUxTNlciFpyhpcLubbB4o4pkATVNQkEfCcav66/0B5wOaSAhxn6r8JKpehx6q+7Dh6uGWR2YIg2rKxoIRYOUYcKZrM7q/s1BTcehb7OvlrMDLeYJHoTdnjfwFkFXgd+CHmnjPOz+DmYZL1JQyCUz5tL3cpxWTKPgEupOUBjIbQE2h+rXomBN9y03o3Gm7VFIF+ySkaXGlGlknU3r5qnWkP/TLguMv0wrofICQfH7QnEhKWa0WT+dCQ0cZWkB41rYFilPmGYc7Sd17Oz+00lXweho4HsD/+JT7/hbu4UNskP2SJ/45DM5JifknAwJJ/+cXeeD89H56753qbt3b3WdNmebLIV7eAfNqr4U</latexit><latexit sha1_base64="dRNZOAdr3+64yfJmCNqaHzngt30=">AAACcXicbVFdS9xAFJ2kttqtrdv6VEQYXGxXhCWRQvtSkPbFBxEt3Q8wS5jM3mxGJ5MwcyMNIT/Cn9Wf0N/Rh746WaOwbi8MnDnn3LkfE+VSGPS8P477bO35i/WNl51Xm6/fbHXfvhuZrNAchjyTmZ5EzIAUCoYoUMIk18DSSMI4uv7e6OMb0EZk6ieWOUxTNlciFpyhpcLubbB4o4pkATVNQkEfCcav66/0B5wOaSAhxn6r8JKpehx6q+7Dh6uGWR2YIg2rKxoIRYOUYcKZrM7q/s1BTcehb7OvlrMDLeYJHoTdnjfwFkFXgd+CHmnjPOz+DmYZL1JQyCUz5tL3cpxWTKPgEupOUBjIbQE2h+rXomBN9y03o3Gm7VFIF+ySkaXGlGlknU3r5qnWkP/TLguMv0wrofICQfH7QnEhKWa0WT+dCQ0cZWkB41rYFilPmGYc7Sd17Oz+00lXweho4HsD/+JT7/hbu4UNskP2SJ/45DM5JifknAwJJ/+cXeeD89H56753qbt3b3WdNmebLIV7eAfNqr4U</latexit><latexit sha1_base64="dRNZOAdr3+64yfJmCNqaHzngt30=">AAACcXicbVFdS9xAFJ2kttqtrdv6VEQYXGxXhCWRQvtSkPbFBxEt3Q8wS5jM3mxGJ5MwcyMNIT/Cn9Wf0N/Rh746WaOwbi8MnDnn3LkfE+VSGPS8P477bO35i/WNl51Xm6/fbHXfvhuZrNAchjyTmZ5EzIAUCoYoUMIk18DSSMI4uv7e6OMb0EZk6ieWOUxTNlciFpyhpcLubbB4o4pkATVNQkEfCcav66/0B5wOaSAhxn6r8JKpehx6q+7Dh6uGWR2YIg2rKxoIRYOUYcKZrM7q/s1BTcehb7OvlrMDLeYJHoTdnjfwFkFXgd+CHmnjPOz+DmYZL1JQyCUz5tL3cpxWTKPgEupOUBjIbQE2h+rXomBN9y03o3Gm7VFIF+ySkaXGlGlknU3r5qnWkP/TLguMv0wrofICQfH7QnEhKWa0WT+dCQ0cZWkB41rYFilPmGYc7Sd17Oz+00lXweho4HsD/+JT7/hbu4UNskP2SJ/45DM5JifknAwJJ/+cXeeD89H56753qbt3b3WdNmebLIV7eAfNqr4U</latexit><latexit sha1_base64="dRNZOAdr3+64yfJmCNqaHzngt30=">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</latexit>
Neighborhood
Self loop
22. GCNs Pipeline
Hidden layer Hidden layer
Input Output
X = H(0)
H(1) H(2)
Z = H(n)
Initial feature
representation of
nodes
Representation
informed by nodes’
neighborhood
[Kipf and Welling,2016]
…
…
…
22
23. GCNs Pipeline
Hidden layer Hidden layer
Input Output
X = H(0)
H(1) H(2)
Z = H(n)
[Kipf and Welling,2016]
…
…
…
Extend GCNs for syntactic dependency trees
Initial feature
representation of
nodes
Representation
informed by nodes’
neighborhood
23
24. Outline
} Semantic Role Labeling
} Graph Convolutional Networks (GCN)
} Syntactic GCN for Semantic Role Labeling (SRL)
} SRL Model
} Exploiting Semantics in Neural MachineTranslation with GCNs
24
35. Syntactic GCNs
Syntactic neighborhood Self-loop is included in N
Messages are direction and
label specific
h(k+1)
v = ReLU
0
@
X
u2N (v)
W
(k)
L(u,v)h(k)
u + b
(k)
L(u,v)
1
A
Message
[Marcheggiani andTitov, 2017]
35
36. } Overparametrized: one matrix for each label-direction pair
}
Syntactic GCNs
Syntactic neighborhood
W
(k)
L(u,v) = V
(k)
dir(u,v)
Self-loop is included in N
Messages are direction and
label specific
h(k+1)
v = ReLU
0
@
X
u2N (v)
W
(k)
L(u,v)h(k)
u + b
(k)
L(u,v)
1
A
Message
[Marcheggiani andTitov, 2017]
36
37. Edge-wise Gates
} Not all edges are equally important for the final task
[Marcheggiani andTitov, 2017]
37
38. Edge-wise Gates
} Not all edges are equally important for the final task
} We should not blindly rely on predicted syntax
[Marcheggiani andTitov, 2017]
38
39. Edge-wise Gates
} Not all edges are equally important for the final task
} We should not blindly rely on predicted syntax
} Gates decide the“importance” of each message
Lane disputed those estimates
NMOD
SBJ
OBJ
ReLU(⌃·) ReLU(⌃·)ReLU(⌃·)ReLU(⌃·)
g g g g g g g g g g
[Marcheggiani andTitov, 2017]
39
40. Edge-wise Gates
} Not all edges are equally important for the final task
} We should not blindly rely on predicted syntax
} Gates decide the“importance” of each message
Gates depend on
nodes and edges Lane disputed those estimates
NMOD
SBJ
OBJ
ReLU(⌃·) ReLU(⌃·)ReLU(⌃·)ReLU(⌃·)
g g g g g g g g g g
[Marcheggiani andTitov, 2017]
40
41. Outline
} Semantic Role Labeling
} Graph Convolutional Networks (GCN)
} Syntactic GCN for Semantic Role Labeling (SRL)
} SRL Model
} Exploiting Semantics in Neural MachineTranslation with GCNs
41
42. Our Model
} Word representation
} Bidirectional LSTM encoder
} GCN Encoder
} Local role classifier
[Marcheggiani andTitov, 2017]
42
43. Word Representation
} Pretrained word embeddings
} Word embeddings
} POS tag embeddings
} Predicate lemma embeddings
Lane disputed those estimates
word
representation
[Marcheggiani andTitov, 2017]
43
44. BiLSTM Encoder
} Encode each word with its left and right context
} Stacked BiLSTM
Lane disputed those estimates
word
representation
J layers
BiLSTM
[Marcheggiani andTitov, 2017]
44
45. GCNs Encoder
} Syntactic GCNs after BiLSTM encoder
} Add syntactic information
} Skip connections
} Longer dependencies are captured
Lane disputed those estimates
word
representation
J layers
BiLSTM
dobj
nmodnsubj
K layers
GCN
[Marcheggiani andTitov, 2017]
45
46. Semantic Role Classifier
Lane disputed those estimates
word
representation
J layers
BiLSTM
dobj
nmodnsubj
K layers
GCN
A1
Classifier
predicate
representation
candidate argument
representation
} Local log-linear classifier
p(r|ti, tp, l) / exp(Wl,r(ti tp))
46
47. Experiments
} Data
} CoNLL-2009 dataset - English and Chinese
} F1 evaluation measure
} Model
} Hyperparameters tuned on English development set
} State-of-the-art predicate disambiguation models
[Marcheggiani andTitov, 2017]
47
54. Syntactic Graph Convolutional Networks
54
} Fast and simple
} Can be seamlessly applied to other tasks
Graph Convolutional Encoders for Syntax-aware Machine Translation
Joost Bastings,IvanTitov,Wilker Aziz,Diego Marcheggiani,Khalil Sima'an.
In Proceedings of EMNLP, 2017.
55. Syntactic Graph Convolutional Networks
55
} Fast and simple
} Can be seamlessly applied to other tasks
Graph Convolutional Encoders for Syntax-aware Machine Translation
Joost Bastings,IvanTitov,Wilker Aziz,Diego Marcheggiani,Khalil Sima'an.
In Proceedings of EMNLP, 2017.
Improvements on
English to German and
English to Czech translations
56. Multi-document Question Answering
56
[De Cao et al., 2018]
• Nodes are entities and edges are co-reference links
• Inference on a graph representing the documents collection
61. Outline
} Semantic Role Labeling
} Graph Convolutional Networks (GCN)
} Syntactic GCN for Semantic Role Labeling (SRL)
} SRL Model
} Exploiting Semantics in Neural MachineTranslation with GCNs
61
62. Motivations [Marcheggiani at al., 2018]
62
John gave his wonderful wife a nice present .
Giver
Thing given
Entity given to
John gave a nice present to his wonderful wife .
Giver
Entity given to
Thing given
63. Motivations
SRL helps to generalize over different surface realizations
of the same underlying “meaning”.
[Marcheggiani at al., 2018]
63
John gave his wonderful wife a nice present .
Giver
Thing given
Entity given to
John gave a nice present to his wonderful wife .
Giver
Entity given to
Thing given
66. Related work
} Semantics in statistical MT
} [Wu and Fung,2009]
} [Liu and Gildea, 2010]
} [Aziz et al., 2011]
} ...
} Syntax in neural MT
} [Sennrich and Haddow,2016]
} [Aharoni and Goldberg,2017 ]
} [Bastings et al., 2017]
} …
} Semantics in neural MT
} ???
[Marcheggiani at al., 2018]
66
67. Predicate-argument encoding
67
John gave his wonderful wife a nice present
WA0
WA1
WA2
WA0’
WA2’
WA1’
Wself
Wself
Wself
Wself
Wself
Wself
Wself
Wself
Semantic
GCN
Semantic
GCN WA0
WA1
WA2
WA0’
WA2’
WA1’
Wself
Wself
Wself
Wself
Wself
Wself
Wself
Wself
Giver
Thing given
Entity given to
68. Our Model
} Standard sequence2sequence with attention
} Semantic GCN encoder on top of a bidirectional RNN
} RNN decoder
[Marcheggiani at al., 2018]
68
69. Our model
John gave his wonderful wife a nice present
WA0
WA1
WA2
WA0’
WA2’
WA1’
Wself
Wself
Wself
Wself
Wself
Wself
Wself
Wself
BiRNN/
CNN
Semantic
GCN
Semantic
GCN WA0
WA1
WA2
WA0’
WA2’
WA1’
Wself
Wself
Wself
Wself
Wself
Wself
Wself
Wself
<bos> John
John
+
RNN
DECODER
ATTENTION
MECHANISM
[Marcheggiani at al., 2018]
69
70. Our model
John gave his wonderful wife a nice present
WA0
WA1
WA2
WA0’
WA2’
WA1’
Wself
Wself
Wself
Wself
Wself
Wself
Wself
Wself
BiRNN/
CNN
Semantic
GCN
Semantic
GCN WA0
WA1
WA2
WA0’
WA2’
WA1’
Wself
Wself
Wself
Wself
Wself
Wself
Wself
Wself
<bos> John
John
+
RNN
DECODER
ATTENTION
MECHANISM
[Marcheggiani at al., 2018]
70
71. Experiments
} Data
} WMT‘16 English-German dataset (~4.5 million sentence pairs)
} BLEU as evaluation measure
} Model
} Hyperparameters tuned on News Commentary En-De (~226K sentence pairs)
} GRU as RNN
[Marcheggiani at al., 2018]
71
79. Analysis
John sold the car to Mark .
Seller Thing sold Buyer
The boy walking down the dusty road is drinking a beer
Walker AM-DIR
Drinker Liquid
SOURCE
SEM GCN
BiRNN John verkaufte das Auto nach Mark .
John verkaufte das Auto an Mark .
SEM GCN
BiRNN Der Junge zu Fuß die staubige Straße ist ein Bier trinken .
Der Junge , der die staubige Straße hinunter geht , trinkt ein Bier .
SOURCE
[Marcheggiani at al., 2018]
79
BiRNN mistranslates “to” as “nach” (directionality)
80. Analysis
John sold the car to Mark .
Seller Thing sold Buyer
The boy walking down the dusty road is drinking a beer
Walker AM-DIR
Drinker Liquid
SOURCE
SEM GCN
BiRNN John verkaufte das Auto nach Mark .
John verkaufte das Auto an Mark .
SEM GCN
BiRNN Der Junge zu Fuß die staubige Straße ist ein Bier trinken .
Der Junge , der die staubige Straße hinunter geht , trinkt ein Bier .
SOURCE
[Marcheggiani at al., 2018]
80
BiRNN mistranslates “to” as “nach” (directionality)
81. John sold the car to Mark .
Seller Thing sold Buyer
The boy walking down the dusty road is drinking a beer
Walker AM-DIR
Drinker Liquid
SOURCE
SEM GCN
BiRNN John verkaufte das Auto nach Mark .
John verkaufte das Auto an Mark .
SEM GCN
BiRNN Der Junge zu Fuß die staubige Straße ist ein Bier trinken .
Der Junge , der die staubige Straße hinunter geht , trinkt ein Bier .
SOURCE
81
BiRNN mistranslates “to” as “nach” (directionality)
Analysis [Marcheggiani at al., 2018]
82. The boy sitting on a bench in the park plays chess .
Thing sitting Location Player Game
AM-LOC
SEM GCN
BiRNN Der Junge zu Fuß die staubige Straße ist ein Bier trinken .
Der Junge , der die staubige Straße hinunter geht , trinkt ein Bier .
SEM GCN
BiRNN Der Junge auf einer Bank im Park spielt Schach .
Der Junge sitzt auf einer Bank im Park Schach .
SOURCE
Analysis [Marcheggiani at al., 2018]
82
Both translations are wrong,
but the BiRNN’s one is grammatically correct
83. The boy sitting on a bench in the park plays chess .
Thing sitting Location Player Game
AM-LOC
SEM GCN
BiRNN Der Junge zu Fuß die staubige Straße ist ein Bier trinken .
Der Junge , der die staubige Straße hinunter geht , trinkt ein Bier .
SEM GCN
BiRNN Der Junge auf einer Bank im Park spielt Schach .
Der Junge sitzt auf einer Bank im Park Schach .
SOURCE
Analysis [Marcheggiani at al., 2018]
83
Both translations are wrong,
but the BiRNN’s one is grammatically correct
84. The boy sitting on a bench in the park plays chess .
Thing sitting Location Player Game
AM-LOC
SEM GCN
BiRNN Der Junge zu Fuß die staubige Straße ist ein Bier trinken .
Der Junge , der die staubige Straße hinunter geht , trinkt ein Bier .
SEM GCN
BiRNN Der Junge auf einer Bank im Park spielt Schach .
Der Junge sitzt auf einer Bank im Park Schach .
SOURCE
Analysis [Marcheggiani at al., 2018]
84
Both translations are wrong,
but the BiRNN’s one is grammatically correct
85. Conclusion
} GCNs for encoding linguistic structures into NN
} Semantics, coreference, discourse
} Fast
} Cheap
} State-of-the-art model for dependency-based SRL
} First to exploit semantics in NMT
85