The document presents four probabilistic models for faceted topic retrieval: MMR, a probabilistic interpretation of MMR, greedy result set pruning, and a probabilistic set-based approach. It describes an experiment comparing these four models on a test collection with 60 queries and human-annotated facets. The probabilistic set-based approach, which estimates facet models and document-facet probabilities, outperformed the other three models in terms of S-recall and redundancy based on a five-fold cross-validation experiment.
Adversarial and reinforcement learning-based approaches to information retrievalBhaskar Mitra
Traditionally, machine learning based approaches to information retrieval have taken the form of supervised learning-to-rank models. Recently, other machine learning approaches—such as adversarial learning and reinforcement learning—have started to find interesting applications in retrieval systems. At Bing, we have been exploring some of these methods in the context of web search. In this talk, I will share couple of our recent work in this area that we presented at SIGIR 2018.
Conformer-Kernel with Query Term Independence @ TREC 2020 Deep Learning TrackBhaskar Mitra
We benchmark Conformer-Kernel models under the strict blind evaluation setting of the TREC 2020 Deep Learning track. In particular, we study the impact of incorporating: (i) Explicit term matching to complement matching based on learned representations (i.e., the “Duet principle”), (ii) query term independence (i.e., the “QTI assumption”) to scale the model to the full retrieval setting, and (iii) the ORCAS click data as an additional document description field. We find evidence which supports that all three aforementioned strategies can lead to improved retrieval quality.
Topic Modeling for Information Retrieval and Word Sense Disambiguation tasksLeonardo Di Donato
Experimental work done regarding the use of Topic Modeling for the implementation and the improvement of some common tasks of Information Retrieval and Word Sense Disambiguation.
First of all it describes the scenario, the pre-processing pipeline realized and the framework used. After we we face a discussion related to the investigation of some different hyperparameters configurations for the LDA algorithm.
This work continues dealing with the retrieval of relevant documents mainly through two different approaches: inferring the topics distribution of the held out document (or query) and comparing it to retrieve similar collection’s documents or through an approach driven by probabilistic querying. The last part of this work is devoted to the investigation of the word sense disambiguation task.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
This report discusses three submissions based on the Duet architecture to the Deep Learning track at TREC 2019. For the document retrieval task, we adapt the Duet model to ingest a "multiple field" view of documents—we refer to the new architecture as Duet with Multiple Fields (DuetMF). A second submission combines the DuetMF model with other neural and traditional relevance estimators in a learning-to-rank framework and achieves improved performance over the DuetMF baseline. For the passage retrieval task, we submit a single run based on an ensemble of eight Duet models.
Adversarial and reinforcement learning-based approaches to information retrievalBhaskar Mitra
Traditionally, machine learning based approaches to information retrieval have taken the form of supervised learning-to-rank models. Recently, other machine learning approaches—such as adversarial learning and reinforcement learning—have started to find interesting applications in retrieval systems. At Bing, we have been exploring some of these methods in the context of web search. In this talk, I will share couple of our recent work in this area that we presented at SIGIR 2018.
Conformer-Kernel with Query Term Independence @ TREC 2020 Deep Learning TrackBhaskar Mitra
We benchmark Conformer-Kernel models under the strict blind evaluation setting of the TREC 2020 Deep Learning track. In particular, we study the impact of incorporating: (i) Explicit term matching to complement matching based on learned representations (i.e., the “Duet principle”), (ii) query term independence (i.e., the “QTI assumption”) to scale the model to the full retrieval setting, and (iii) the ORCAS click data as an additional document description field. We find evidence which supports that all three aforementioned strategies can lead to improved retrieval quality.
Topic Modeling for Information Retrieval and Word Sense Disambiguation tasksLeonardo Di Donato
Experimental work done regarding the use of Topic Modeling for the implementation and the improvement of some common tasks of Information Retrieval and Word Sense Disambiguation.
First of all it describes the scenario, the pre-processing pipeline realized and the framework used. After we we face a discussion related to the investigation of some different hyperparameters configurations for the LDA algorithm.
This work continues dealing with the retrieval of relevant documents mainly through two different approaches: inferring the topics distribution of the held out document (or query) and comparing it to retrieve similar collection’s documents or through an approach driven by probabilistic querying. The last part of this work is devoted to the investigation of the word sense disambiguation task.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
This report discusses three submissions based on the Duet architecture to the Deep Learning track at TREC 2019. For the document retrieval task, we adapt the Duet model to ingest a "multiple field" view of documents—we refer to the new architecture as Duet with Multiple Fields (DuetMF). A second submission combines the DuetMF model with other neural and traditional relevance estimators in a learning-to-rank framework and achieves improved performance over the DuetMF baseline. For the passage retrieval task, we submit a single run based on an ensemble of eight Duet models.
Neural Models for Information RetrievalBhaskar Mitra
In the last few years, neural representation learning approaches have achieved very good performance on many natural language processing (NLP) tasks, such as language modelling and machine translation. This suggests that neural models will also yield significant performance improvements on information retrieval (IR) tasks, such as relevance ranking, addressing the query-document vocabulary mismatch problem by using semantic rather than lexical matching. IR tasks, however, are fundamentally different from NLP tasks leading to new challenges and opportunities for existing neural representation learning approaches for text.
We begin this talk with a discussion on text embedding spaces for modelling different types of relationships between items which makes them suitable for different IR tasks. Next, we present how topic-specific representations can be more effective than learning global embeddings. Finally, we conclude with an emphasis on dealing with rare terms and concepts for IR, and how embedding based approaches can be augmented with neural models for lexical matching for better retrieval performance. While our discussions are grounded in IR tasks, the findings and the insights covered during this talk should be generally applicable to other NLP and machine learning tasks.
Neural Information Retrieval: In search of meaningful progressBhaskar Mitra
The emergence of deep learning based methods for search poses several challenges and opportunities not just for modeling, but also for benchmarking and measuring progress in the field. Some of these challenges are new, while others have evolved from existing challenges in IR benchmarking exacerbated by the scale at which deep learning models operate. Evaluation efforts such as the TREC Deep Learning track and the MS MARCO public leaderboard are intended to encourage research and track our progress, addressing big questions in our field. The goal is not simply to identify which run is "best" but to move the field forward by developing new robust techniques, that work in many different settings, and are adopted in research and practice. This entails a wider conversation in the IR community about what constitutes meaningful progress, how benchmark design can encourage or discourage certain outcomes, and about the validity of our findings. In this talk, I will present a brief overview of what we have learned from our work on MS MARCO and the TREC Deep Learning track--and reflect on the state of the field and the road ahead.
Survey of Generative Clustering Models 2008Roman Stanchak
Survey of Generative Clustering Models "Probabilistic Topic Models" circa 2008. Class presentation by Roman Stanchak and Prithviraj Sen for University of Maryland College Park cmsc828g, Link Mining and Dynamic Graph Analysis. Spring 2008. Instructor: Prof. Lise Getoor
The (standard) Boolean model of information retrieval (BIR) is a classical information retrieval (IR) model and, at the same time, the first and most-adopted one. ... The BIR is based on Boolean logic and classical set theory in that both the documents to be searched and the user's query are conceived as sets of terms.
A fundamental goal of search engines is to identify, given a query, documents that have relevant text. This is intrinsically difficult because the query and the document may use different vocabulary, or the document may contain query words without being relevant. We investigate neural word embeddings as a source of evidence in document ranking. We train a word2vec embedding model on a large unlabelled query corpus, but in contrast to how the model is commonly used, we retain both the input and the output projections, allowing us to leverage both the embedding spaces to derive richer distributional relationships. During ranking we map the query words into the input space and the document words into the output space, and compute a query-document relevance score by aggregating the cosine similarities across all the query-document word pairs.
We postulate that the proposed Dual Embedding Space Model (DESM) captures evidence on whether a document is about a query term in addition to what is modelled by traditional term-frequency based approaches. Our experiments show that the DESM can re-rank top documents returned by a commercial Web search engine, like Bing, better than a term-matching based signal like TF-IDF. However, when ranking a larger set of candidate documents, we find the embeddings-based approach is prone to false positives, retrieving documents that are only loosely related to the query. We demonstrate that this problem can be solved effectively by ranking based on a linear mixture of the DESM and the word counting features.
A FILM SYNOPSIS GENRE CLASSIFIER BASED ON MAJORITY VOTEijnlc
We propose an automatic classification system of movie genres based on different features from their textual synopsis. Our system is first trained on thousands of movie synopsis from online open databases, by learning relationships between textual signatures and movie genres. Then it is tested on other movie synopsis, and its results are compared to the true genres obtained from the Wikipedia and the Open Movie Database
(OMDB) databases. The results show that our algorithm achieves a classification accuracy exceeding 75%.
Document ranking using qprp with concept of multi dimensional subspacePrakash Dubey
qPRP is the new model for IR. Existing qPRP approach considers term present in different section of document equally. Our belief is that representing the document as multidimensional subspace will give better result. Because each section of document as its own importance.
Neural Models for Information RetrievalBhaskar Mitra
In the last few years, neural representation learning approaches have achieved very good performance on many natural language processing (NLP) tasks, such as language modelling and machine translation. This suggests that neural models will also yield significant performance improvements on information retrieval (IR) tasks, such as relevance ranking, addressing the query-document vocabulary mismatch problem by using semantic rather than lexical matching. IR tasks, however, are fundamentally different from NLP tasks leading to new challenges and opportunities for existing neural representation learning approaches for text.
We begin this talk with a discussion on text embedding spaces for modelling different types of relationships between items which makes them suitable for different IR tasks. Next, we present how topic-specific representations can be more effective than learning global embeddings. Finally, we conclude with an emphasis on dealing with rare terms and concepts for IR, and how embedding based approaches can be augmented with neural models for lexical matching for better retrieval performance. While our discussions are grounded in IR tasks, the findings and the insights covered during this talk should be generally applicable to other NLP and machine learning tasks.
Neural Information Retrieval: In search of meaningful progressBhaskar Mitra
The emergence of deep learning based methods for search poses several challenges and opportunities not just for modeling, but also for benchmarking and measuring progress in the field. Some of these challenges are new, while others have evolved from existing challenges in IR benchmarking exacerbated by the scale at which deep learning models operate. Evaluation efforts such as the TREC Deep Learning track and the MS MARCO public leaderboard are intended to encourage research and track our progress, addressing big questions in our field. The goal is not simply to identify which run is "best" but to move the field forward by developing new robust techniques, that work in many different settings, and are adopted in research and practice. This entails a wider conversation in the IR community about what constitutes meaningful progress, how benchmark design can encourage or discourage certain outcomes, and about the validity of our findings. In this talk, I will present a brief overview of what we have learned from our work on MS MARCO and the TREC Deep Learning track--and reflect on the state of the field and the road ahead.
Survey of Generative Clustering Models 2008Roman Stanchak
Survey of Generative Clustering Models "Probabilistic Topic Models" circa 2008. Class presentation by Roman Stanchak and Prithviraj Sen for University of Maryland College Park cmsc828g, Link Mining and Dynamic Graph Analysis. Spring 2008. Instructor: Prof. Lise Getoor
The (standard) Boolean model of information retrieval (BIR) is a classical information retrieval (IR) model and, at the same time, the first and most-adopted one. ... The BIR is based on Boolean logic and classical set theory in that both the documents to be searched and the user's query are conceived as sets of terms.
A fundamental goal of search engines is to identify, given a query, documents that have relevant text. This is intrinsically difficult because the query and the document may use different vocabulary, or the document may contain query words without being relevant. We investigate neural word embeddings as a source of evidence in document ranking. We train a word2vec embedding model on a large unlabelled query corpus, but in contrast to how the model is commonly used, we retain both the input and the output projections, allowing us to leverage both the embedding spaces to derive richer distributional relationships. During ranking we map the query words into the input space and the document words into the output space, and compute a query-document relevance score by aggregating the cosine similarities across all the query-document word pairs.
We postulate that the proposed Dual Embedding Space Model (DESM) captures evidence on whether a document is about a query term in addition to what is modelled by traditional term-frequency based approaches. Our experiments show that the DESM can re-rank top documents returned by a commercial Web search engine, like Bing, better than a term-matching based signal like TF-IDF. However, when ranking a larger set of candidate documents, we find the embeddings-based approach is prone to false positives, retrieving documents that are only loosely related to the query. We demonstrate that this problem can be solved effectively by ranking based on a linear mixture of the DESM and the word counting features.
A FILM SYNOPSIS GENRE CLASSIFIER BASED ON MAJORITY VOTEijnlc
We propose an automatic classification system of movie genres based on different features from their textual synopsis. Our system is first trained on thousands of movie synopsis from online open databases, by learning relationships between textual signatures and movie genres. Then it is tested on other movie synopsis, and its results are compared to the true genres obtained from the Wikipedia and the Open Movie Database
(OMDB) databases. The results show that our algorithm achieves a classification accuracy exceeding 75%.
Document ranking using qprp with concept of multi dimensional subspacePrakash Dubey
qPRP is the new model for IR. Existing qPRP approach considers term present in different section of document equally. Our belief is that representing the document as multidimensional subspace will give better result. Because each section of document as its own importance.
Topic modeling of marketing scientific papers: An experimental surveyICDEcCnferenece
Malek Chebil, Rim Jallouli, Mohamed Anis Bach Tobji and Chiheb Eddine Ben Ncir. Topic modeling of marketing scientific papers: An experimental survey. (ICDEc 2021)
EFFICIENTLY PROCESSING OF TOP-K TYPICALITY QUERY FOR STRUCTURED DATAcsandit
This work presents a novel ranking scheme for structured data. We show how to apply the
notion of typicality analysis from cognitive science and how to use this notion to formulate the
problem of ranking data with categorical attributes. First, we formalize the typicality query
model for relational databases. We adopt Pearson correlation coefficient to quantify the extent
of the typicality of an object. The correlation coefficient estimates the extent of statistical
relationships between two variables based on the patterns of occurrences and absences of their
values. Second, we develop a top-k query processing method for efficient computation. TPFilter
prunes unpromising objects based on tight upper bounds and selectively joins tuples of highest
typicality score. Our methods efficiently prune unpromising objects based on upper bounds.
Experimental results show our approach is promising for real data.
Building Learning to Rank (LTR) search reranking models using Large Language ...Sujit Pal
Search engineers have many tools to address relevance. Older tools are typically unsupervised (statistical, rule based) and require large investments in manual tuning effort. Newer ones involve training or fine-tuning machine learning models and vector search, which require large investments in labeling documents with their relevance to queries.
Learning to Rank (LTR) models are in the latter category. However, their popularity has traditionally been limited to domains where user data can be harnessed to generate labels that are cheap and plentiful, such as e-commerce sites. In domains where this is not true, labeling often involves human experts, and results in labels that are neither cheap nor plentiful. This effectively becomes a roadblock to adoption of LTR models in these domains, in spite of their effectiveness in general.
Generative Large Language Models (LLMs) with parameters in the 70B+ range have been found to perform well at tasks that require mimicking human preferences. Labeling query-document pairs with relevance judgements for training LTR models is one such task. Using LLMs for this task opens up the possibility of obtaining a potentially unlimited number of query judgment labels, and makes LTR models a viable approach to improving the site’s search relevancy.
In this presentation, we describe work that was done to train and evaluate four LTR based re-rankers against lexical, vector, and heuristic search baselines. The models were a mix of pointwise, pairwise and listwise, and required different strategies to generate labels for them. All four models outperformed the lexical baseline, and one of the four models outperformed the vector search baseline as well. None of the models beat the heuristics baseline, although two came close – however, it is important to note that the heuristics were built up over months of trial and error and required familiarity of the search domain, whereas the LTR models were built in days and required much less familiarity.
Keyword-based linked data information retrieval is an easy choice for general purpose users, but implementation of such approach is a challenge because mere keyword does not hold semantics. Some studies have incorporated templates in an eort to bridge this gap, but most such pproaches have proven ineective because of inecient template management. Because linked data can be resented in a structured format, we can assume that the data's internal statistics can be used to eectively in
uence template management. In this work, we explore
the use of this in uence for template creation, ranking, and scaling. Then, we demonstrate how our proposal for automatic linked data information retrieval can be used alongside familiar keyword-based information retrieval methods, and can also be incorporated alongside other techniques, such as ontology inclusion and sophisticated matching, to achieve increased levels of performance.
Models for Information Retrieval and RecommendationArjen de Vries
Online information services personalize the user experience by applying recommendation systems to identify the information that is most relevant to the user. The question how to estimate relevance has been the core concept in the field of information retrieval for many years. Not so surprisingly then, it turns out that the methods used in online recommendation systems are closely related to the models developed in the information retrieval area. In this lecture, I present a unified approach to information retrieval and collaborative filtering, and demonstrate how this let’s us turn a standard information retrieval system into a state-of-the-art recommendation system.
Spam filtering poses a critical problem in
text categorization as the features of text is
continuously changing. Spam evolves continuously and
makes it difficult for the filter to classify the evolving
and evading new feature patterns. Most practical
applications are based on online user feedback, the
task calls for fast, incremental and robust learning
algorithms. This paper presents a system for
automatically detection and filtering of unsolicited
electronic messages. In this paper, we have developed
a content-based classifier, which uses two topic models
LSI and PLSA complemented with a text patternmatching
based natural language approach. By
combining these powerful statistical and NLP
techniques we obtained a parallel content based Spam
filter, which performs the filtration in two stages. In
the first stage each model generates its individual
predictions, which are combined by a voting
mechanism as the second stage.
Similar to Probabilistic Models of Novel Document Rankings for Faceted Topic Retrieval (20)
As Europe's leading economic powerhouse and the fourth-largest hashtag#economy globally, Germany stands at the forefront of innovation and industrial might. Renowned for its precision engineering and high-tech sectors, Germany's economic structure is heavily supported by a robust service industry, accounting for approximately 68% of its GDP. This economic clout and strategic geopolitical stance position Germany as a focal point in the global cyber threat landscape.
In the face of escalating global tensions, particularly those emanating from geopolitical disputes with nations like hashtag#Russia and hashtag#China, hashtag#Germany has witnessed a significant uptick in targeted cyber operations. Our analysis indicates a marked increase in hashtag#cyberattack sophistication aimed at critical infrastructure and key industrial sectors. These attacks range from ransomware campaigns to hashtag#AdvancedPersistentThreats (hashtag#APTs), threatening national security and business integrity.
🔑 Key findings include:
🔍 Increased frequency and complexity of cyber threats.
🔍 Escalation of state-sponsored and criminally motivated cyber operations.
🔍 Active dark web exchanges of malicious tools and tactics.
Our comprehensive report delves into these challenges, using a blend of open-source and proprietary data collection techniques. By monitoring activity on critical networks and analyzing attack patterns, our team provides a detailed overview of the threats facing German entities.
This report aims to equip stakeholders across public and private sectors with the knowledge to enhance their defensive strategies, reduce exposure to cyber risks, and reinforce Germany's resilience against cyber threats.
Opendatabay - Open Data Marketplace.pptxOpendatabay
Opendatabay.com unlocks the power of data for everyone. Open Data Marketplace fosters a collaborative hub for data enthusiasts to explore, share, and contribute to a vast collection of datasets.
First ever open hub for data enthusiasts to collaborate and innovate. A platform to explore, share, and contribute to a vast collection of datasets. Through robust quality control and innovative technologies like blockchain verification, opendatabay ensures the authenticity and reliability of datasets, empowering users to make data-driven decisions with confidence. Leverage cutting-edge AI technologies to enhance the data exploration, analysis, and discovery experience.
From intelligent search and recommendations to automated data productisation and quotation, Opendatabay AI-driven features streamline the data workflow. Finding the data you need shouldn't be a complex. Opendatabay simplifies the data acquisition process with an intuitive interface and robust search tools. Effortlessly explore, discover, and access the data you need, allowing you to focus on extracting valuable insights. Opendatabay breaks new ground with a dedicated, AI-generated, synthetic datasets.
Leverage these privacy-preserving datasets for training and testing AI models without compromising sensitive information. Opendatabay prioritizes transparency by providing detailed metadata, provenance information, and usage guidelines for each dataset, ensuring users have a comprehensive understanding of the data they're working with. By leveraging a powerful combination of distributed ledger technology and rigorous third-party audits Opendatabay ensures the authenticity and reliability of every dataset. Security is at the core of Opendatabay. Marketplace implements stringent security measures, including encryption, access controls, and regular vulnerability assessments, to safeguard your data and protect your privacy.
Data Centers - Striving Within A Narrow Range - Research Report - MCG - May 2...pchutichetpong
M Capital Group (“MCG”) expects to see demand and the changing evolution of supply, facilitated through institutional investment rotation out of offices and into work from home (“WFH”), while the ever-expanding need for data storage as global internet usage expands, with experts predicting 5.3 billion users by 2023. These market factors will be underpinned by technological changes, such as progressing cloud services and edge sites, allowing the industry to see strong expected annual growth of 13% over the next 4 years.
Whilst competitive headwinds remain, represented through the recent second bankruptcy filing of Sungard, which blames “COVID-19 and other macroeconomic trends including delayed customer spending decisions, insourcing and reductions in IT spending, energy inflation and reduction in demand for certain services”, the industry has seen key adjustments, where MCG believes that engineering cost management and technological innovation will be paramount to success.
MCG reports that the more favorable market conditions expected over the next few years, helped by the winding down of pandemic restrictions and a hybrid working environment will be driving market momentum forward. The continuous injection of capital by alternative investment firms, as well as the growing infrastructural investment from cloud service providers and social media companies, whose revenues are expected to grow over 3.6x larger by value in 2026, will likely help propel center provision and innovation. These factors paint a promising picture for the industry players that offset rising input costs and adapt to new technologies.
According to M Capital Group: “Specifically, the long-term cost-saving opportunities available from the rise of remote managing will likely aid value growth for the industry. Through margin optimization and further availability of capital for reinvestment, strong players will maintain their competitive foothold, while weaker players exit the market to balance supply and demand.”
Adjusting primitives for graph : SHORT REPORT / NOTESSubhajit Sahu
Graph algorithms, like PageRank Compressed Sparse Row (CSR) is an adjacency-list based graph representation that is
Multiply with different modes (map)
1. Performance of sequential execution based vs OpenMP based vector multiply.
2. Comparing various launch configs for CUDA based vector multiply.
Sum with different storage types (reduce)
1. Performance of vector element sum using float vs bfloat16 as the storage type.
Sum with different modes (reduce)
1. Performance of sequential execution based vs OpenMP based vector element sum.
2. Performance of memcpy vs in-place based CUDA based vector element sum.
3. Comparing various launch configs for CUDA based vector element sum (memcpy).
4. Comparing various launch configs for CUDA based vector element sum (in-place).
Sum with in-place strategies of CUDA mode (reduce)
1. Comparing various launch configs for CUDA based vector element sum (in-place).
Probabilistic Models of Novel Document Rankings for Faceted Topic Retrieval
1. Probabilistic Models of NovelProbabilistic Models of Novel
Document Rankings forDocument Rankings for
Faceted Topic RetrievalFaceted Topic Retrieval
Ben Cartrette and Praveen Chandar
Dept. of Computer and Information Science
University of Delaware
Newark, DE
( CIKM ’09 )
Date: 2010/05/03
Speaker: Lin, Yi-Jhen
Advisor: Dr. Koh, Jia-Ling
3. Introduction - MotivationIntroduction - Motivation
Modeling documents as independently
relevant does not necessarily provide the
optimal user experience.
5. IntroductionIntroduction
Novelty and diversity become the
new definition of relevance and
evaluation measures .
They can be achieved through
retrieving documents that are
relevant to query, but cover different
facets of the topic.
we call faceted topic retrieval !
6. Introduction - GoalIntroduction - Goal
The faceted topic retrieval system
must be able to find a small set of
documents that covers all of the
facets
3 documents that cover 10 facets is
preferable to 5 documents that cover
10 facets
7. Faceted Topic Retrieval - TaskFaceted Topic Retrieval - Task
Define the task in terms of
Information need :
A faceted topic retrieval information need
is one that has a set of answers – facets –
that are clearly delineated
How that need is best satisfied :
Each answer is fully contained within at
least one document
8. Faceted Topic Retrieval - TaskFaceted Topic Retrieval - Task
Information need
invest in next generation technologies
increase use of renewable energy sources
Invest in renewable energy sources
double ethanol in gas supply
shift to biodiesel
shift to coal
Facets (a set of
answers)
9. Faceted Topic RetrievalFaceted Topic Retrieval
A Query :
A sort list of keywords
A ranked list of documents
that contain as many unique
facets as possible.
D1D1
DnDn
D2D2
11. Evaluation –Evaluation –
an example for S-recall and S-precisionan example for S-recall and S-precision
Total : 10 facets (assume all facets in
documents are non-overlapped)
13. Faceted topic retrieval modelsFaceted topic retrieval models
4 kinds of models
- MMR (Maximal Marginal Relevance)
- Probabilistic Interpretation of MMR
- Greedy Result Set Pruning
- A Probabilistic Set-Based Approach
14. 1. MMR1. MMR
2. Probabilistic2. Probabilistic
Interpretation of MMRInterpretation of MMR
Let c1=0, c3=c4
15. 3. Greedy Result Set Pruning3. Greedy Result Set Pruning
First, rank without considering
novelty (in order of relevance)
Second, step down the list of
documents, prune documents with
similarity greater than some
threshold ϴ
I.e., at rank i, remove any document Dj,
j > i, with sim(Dj,Di) > ϴ
16. 4. A Probabilistic Set-Based4. A Probabilistic Set-Based
ApproachApproach
P(F ϵ D) :Probability of D contains F
the probability that a facet Fj occurs in at
least one document in a set D is
the probability that all of the facets in a
set F are captured by the documents D is
17. 4. A Probabilistic Set-Based4. A Probabilistic Set-Based
ApproachApproach
4.1 Hypothesizing Facets
4.2 Estimating Document-Facet
Probabilities
4.3 Maximizing Likelihood
18. 4.1 Hypothesizing Facets4.1 Hypothesizing Facets
Two unsupervised probabilistic methods :
Relevance modeling
Topic modeling with LDA
Instead of extract facets directly
from any particular word or phrase,
we build a “ facet model ”P(w|F)
19. 4.1 Hypothesizing Facets4.1 Hypothesizing Facets
Since we do not know the facet
terms or the set of documents
relevant to the facet, we will
estimate them from the retrieved
documents
Obtain m models from the top m
retrieved documents by taking each
document along with its k nearest
neighbors as the basis for a facet
model
20. Relevance modelingRelevance modeling
Estimate m ”facet models“ P(w|Fj)
from a set of retrieved documents
using the so-called RM2 approach:
DFj : the set of documents relevant to facet Fj
fk : facet terms
21. Topic modeling with LDATopic modeling with LDA
Probabilistic P(w|Fj) and P(Fj) can
found through expectation
maximization
22. 4.2 Estimating Document-Facet4.2 Estimating Document-Facet
ProbabilitiesProbabilities
Both the facet relevance model and LDA
model produce generation probabilistic
P(Di|Fj)
P(Di|Fj) : the probability that sampling
terms from the facet model Fj will
produce document Di
23. 4.3 Maximizing Likelihood4.3 Maximizing Likelihood
Define the likelihood function
Constrain :
K : hypothesized minimum number
required to cover the facets
Maximizing L(y) is a NP-Hard problem
Approximate solution :
For each facet Fj, take the document Di
with maximum
24. Experiment - DataExperiment - Data
A Query :
A sort list of keywords
Top 130 retrieved documents
D1D1
D130D130
D2D2
Query Likelihood L.M.
25. Experiment - DataExperiment - Data
Top 130 retrieved
documents
D1D1
D130D130
D2D2
2 assessors
to judge
44.7 relevant documents per
query
Each document contains 4.3
facets
39.2 unique facets on average
( for average one unique facet
per relevant document )
Agreement :
72% of all relevant documents
were judged relevant by both
assessors
For 60 queries :
27. Experiment – Retrieval EnginesExperiment – Retrieval Engines
Using Lemur toolkit
LM baseline: a query-likelihood language model
RM baseline: a pseudo-feedback with relevance
model
MMR: query similarity scores from LM baseline
and cosine similarity for novelty
AvgMix (Prob MMR) : the probabilistic MMR
model using query-likelihood scores from LM
baseline and the AvgMix novelty score.
Pruning: removing documents from the LM
baseline on cosine similarity
FM: the set-based facet model
28. Experiment – Retrieval EnginesExperiment – Retrieval Engines
FM: the set-based facet model
FM-RM:
each of the top m documents and their K nearest
neighbors becomes a “facet model ”P(w|Fj), then
compute the probability P(Di|Fj)
FM-LDA:
use LDA to discover subtopics zj, and get P(zj|
D) , we extract 50 subtopics
29. Experiments - EvaluationExperiments - Evaluation
Use five-fold cross-validation to
train and test systems
48 queries in four folds to train
model parameters
Parameters are used to obtain
ranked results on the remaining 12
queries
At the minimum optimal rank S-
rec, we report S-recall, redundancy,
MAP
32. ConclusionConclusion
We defined a type of novelty retrieval
task called faceted topic retrieval
retrieve the facets of information need
in a small set of documents.
We presented two novel models: One
that prunes a retrieval ranking and
one a formally-motivated probabilistic
models.
Both models are competitive with
MMR, and outperform another
probabilistic model.