This document proposes a method to train dependency parser models without manually annotated data by:
1) Creating an initial "blank" model that outputs unlabeled dependencies
2) Parsing an unannotated corpus with the blank model and logging the decisions
3) Extracting heuristics from the parse decisions to identify common dependency patterns
4) Generating new training examples by modifying the logged decisions based on the heuristics
5) Retraining the model on the generated examples, which improves the parser outputs over the blank model. Further work to optimize efficiency and heuristic analysis is suggested.
Transition-based Dependency Parsing with Selectional BranchingJinho Choi
We present a novel approach, called selectional branching, which uses confidence estimates to decide when to employ a beam, providing the accuracy of beam search at speeds close to a greedy transition-based dependency parsing approach. Selectional branching is guaranteed to perform a fewer number of transitions than beam search yet performs as accurately. We also present a new transition-based dependency parsing algorithm that gives a complexity of O(n) for projective parsing and an expected linear time speed for non-projective parsing. With the standard setup, our parser shows an unlabeled attachment score of 92.96% and a parsing speed of 9 milliseconds per sentence, which is faster and more accurate than the current state-of-the-art transition- based parser that uses beam search.
Dependency Parsing Algorithms Analysis - Major Project Bhuvnesh Pratap
Comparison of the performance of Dependency Parsing Algorithms. Department of Computer Science, Indian Institute of Information Technology, Design & Manufacturing
This report shows what a dependency structure is, why a dependency structure is useful, and how to parse natural sentences to dependency structures. The report describes two stat-of-art dependency parsers, MaltParser and MSTParser, and shows comparisons between the parsers and ways to integrate them. Finally, it suggests a new parsing algorithm and possible applications using dependency structures.
Transition-based Dependency Parsing with Selectional BranchingJinho Choi
We present a novel approach, called selectional branching, which uses confidence estimates to decide when to employ a beam, providing the accuracy of beam search at speeds close to a greedy transition-based dependency parsing approach. Selectional branching is guaranteed to perform a fewer number of transitions than beam search yet performs as accurately. We also present a new transition-based dependency parsing algorithm that gives a complexity of O(n) for projective parsing and an expected linear time speed for non-projective parsing. With the standard setup, our parser shows an unlabeled attachment score of 92.96% and a parsing speed of 9 milliseconds per sentence, which is faster and more accurate than the current state-of-the-art transition- based parser that uses beam search.
Dependency Parsing Algorithms Analysis - Major Project Bhuvnesh Pratap
Comparison of the performance of Dependency Parsing Algorithms. Department of Computer Science, Indian Institute of Information Technology, Design & Manufacturing
This report shows what a dependency structure is, why a dependency structure is useful, and how to parse natural sentences to dependency structures. The report describes two stat-of-art dependency parsers, MaltParser and MSTParser, and shows comparisons between the parsers and ways to integrate them. Finally, it suggests a new parsing algorithm and possible applications using dependency structures.
Proactive Empirical Assessment of New Language Feature Adoption via Automated...Raffi Khatchadourian
Programming languages and platforms improve over time, sometimes resulting in new language features that offer many benefits. However, despite these benefits, developers may not always be willing to adopt them in their projects for various reasons. In this paper, we describe an empirical study where we assess the adoption of a particular new language feature. Studying how developers use (or do not use) new language features is important in programming language research and engineering because it gives designers insight into the usability of the language to create meaning programs in that language. This knowledge, in turn, can drive future innovations in the area. Here, we explore Java 8 default methods, which allow interfaces to contain (instance) method implementations.
Default methods can ease interface evolution, make certain ubiquitous design patterns redundant, and improve both modularity and maintainability. A focus of this work is to discover, through a scientific approach and a novel technique, situations where developers found these constructs useful and where they did not, and the reasons for each. Although several studies center around assessing new language features, to the best of our knowledge, this kind of construct has not been previously considered.
Despite their benefits, we found that developers did not adopt default methods in all situations. Our study consisted of submitting pull requests introducing the language feature to 19 real-world, open source Java projects without altering original program semantics. This novel assessment technique is proactive in that the adoption was driven by an automatic refactoring approach rather than waiting for developers to discover and integrate the feature themselves. In this way, we set forth best practices and patterns of using the language feature effectively earlier rather than later and are able to possibly guide (near) future language evolution. We foresee this technique to be useful in assessing other new language features, design patterns, and other programming idioms.
Strata San Jose 2016: Scalable Ensemble Learning with H2OSri Ambati
Erin LeDell's presentation on Scalable Ensemble Learning with H2O at Strata + Hadoop World San Jose, 03.29.16
- Powered by the open source machine learning software H2O.ai. Contributors welcome at: https://github.com/h2oai
- To view videos on H2O open source machine learning software, go to: https://www.youtube.com/user/0xdata
This presentation talks about Natural Language Processing using Java. At Museaic, a music intelligence platform, we spent time figuring out how to extract central themes from song lyrics. In this talk, I will cover some of the tasks involved in natural language processing such as named entity recognition, word sense disambiguation and concept/theme extraction. I will also cover libraries available in java such as stanford-nlp, dbpedia-spotlight and graph approaches using WordNet and semantic databases. This talk would help people understand text processing beyond simple keyword approaches and provide them with some of the best techniques/libraries for it in the Java world.
Mendeley’s Research Catalogue: building it, opening it up and making it even ...Kris Jack
Presentation given at Workshop on Academic-Industrial Collaborations for Recommender Systems 2013 (http://bit.ly/114XDsE), JCDL'13. A walk through Mendeley as a platform, growing pains involved with engineering at a large scale, the data that we're making publicly available and some demos that have come out of academic collaborations.
Best Practices for Hyperparameter Tuning with MLflowDatabricks
Hyperparameter tuning and optimization is a powerful tool in the area of AutoML, for both traditional statistical learning models as well as for deep learning. There are many existing tools to help drive this process, including both blackbox and whitebox tuning. In this talk, we'll start with a brief survey of the most popular techniques for hyperparameter tuning (e.g., grid search, random search, Bayesian optimization, and parzen estimators) and then discuss the open source tools which implement each of these techniques. Finally, we will discuss how we can leverage MLflow with these tools and techniques to analyze how our search is performing and to productionize the best models.
Speaker: Joseph Bradley
GPT-2: Language Models are Unsupervised Multitask LearnersYoung Seok Kim
Review of paper
Language Models are Unsupervised Multitask Learners
(GPT-2)
by Alec Radford et al.
Paper link: https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf
YouTube presentation: https://youtu.be/f5zULULWUwM
(Slides are written in English, but the presentation is done in Korean)
This slide deck provides a survey of research in the field of coreference resolution. We survey 10 significant research papers and also provide a detailed description of the problem and also suggest future research directions.
Apply chinese radicals into neural machine translation: deeper than character...Lifeng (Aaron) Han
LPRC 2018: Limerick Postgraduate Research Conference
Lifeng Han and Shaohui Kuang. 2018. Apply Chinese radicals into neural machine translation: Deeper than character level. ArXiv pre-print https://arxiv.org/abs/1805.01565v1
Webinar at AgileTD Mondays: Mind maps to support exploratory testing: a team ...Claudia Badell
This webinar is about how mind maps are used to support exploratory testing in a cross-functional team. Claudia will share how mind maps help the team to have a common understanding of what to test, and how mind maps are designed by the team in a way that they can easily be read and understood regardless who created them. She will also present how mind maps are re-used through the different releases. At the end of the webinar, Claudia will share what they have learned as a team when applying this testing strategy.
This story is set during the process of building a multi-platform UI prototyping tool mainly for interaction designers. The team, fully dedicated to building the product, consists of highly qualified and experienced professionals: developers (7), interaction designers (1), visual designers (1), technical writers (1), and testers (1).
Duration: 20 minutes
Proactive Empirical Assessment of New Language Feature Adoption via Automated...Raffi Khatchadourian
Programming languages and platforms improve over time, sometimes resulting in new language features that offer many benefits. However, despite these benefits, developers may not always be willing to adopt them in their projects for various reasons. In this paper, we describe an empirical study where we assess the adoption of a particular new language feature. Studying how developers use (or do not use) new language features is important in programming language research and engineering because it gives designers insight into the usability of the language to create meaning programs in that language. This knowledge, in turn, can drive future innovations in the area. Here, we explore Java 8 default methods, which allow interfaces to contain (instance) method implementations.
Default methods can ease interface evolution, make certain ubiquitous design patterns redundant, and improve both modularity and maintainability. A focus of this work is to discover, through a scientific approach and a novel technique, situations where developers found these constructs useful and where they did not, and the reasons for each. Although several studies center around assessing new language features, to the best of our knowledge, this kind of construct has not been previously considered.
Despite their benefits, we found that developers did not adopt default methods in all situations. Our study consisted of submitting pull requests introducing the language feature to 19 real-world, open source Java projects without altering original program semantics. This novel assessment technique is proactive in that the adoption was driven by an automatic refactoring approach rather than waiting for developers to discover and integrate the feature themselves. In this way, we set forth best practices and patterns of using the language feature effectively earlier rather than later and are able to possibly guide (near) future language evolution. We foresee this technique to be useful in assessing other new language features, design patterns, and other programming idioms.
Strata San Jose 2016: Scalable Ensemble Learning with H2OSri Ambati
Erin LeDell's presentation on Scalable Ensemble Learning with H2O at Strata + Hadoop World San Jose, 03.29.16
- Powered by the open source machine learning software H2O.ai. Contributors welcome at: https://github.com/h2oai
- To view videos on H2O open source machine learning software, go to: https://www.youtube.com/user/0xdata
This presentation talks about Natural Language Processing using Java. At Museaic, a music intelligence platform, we spent time figuring out how to extract central themes from song lyrics. In this talk, I will cover some of the tasks involved in natural language processing such as named entity recognition, word sense disambiguation and concept/theme extraction. I will also cover libraries available in java such as stanford-nlp, dbpedia-spotlight and graph approaches using WordNet and semantic databases. This talk would help people understand text processing beyond simple keyword approaches and provide them with some of the best techniques/libraries for it in the Java world.
Mendeley’s Research Catalogue: building it, opening it up and making it even ...Kris Jack
Presentation given at Workshop on Academic-Industrial Collaborations for Recommender Systems 2013 (http://bit.ly/114XDsE), JCDL'13. A walk through Mendeley as a platform, growing pains involved with engineering at a large scale, the data that we're making publicly available and some demos that have come out of academic collaborations.
Best Practices for Hyperparameter Tuning with MLflowDatabricks
Hyperparameter tuning and optimization is a powerful tool in the area of AutoML, for both traditional statistical learning models as well as for deep learning. There are many existing tools to help drive this process, including both blackbox and whitebox tuning. In this talk, we'll start with a brief survey of the most popular techniques for hyperparameter tuning (e.g., grid search, random search, Bayesian optimization, and parzen estimators) and then discuss the open source tools which implement each of these techniques. Finally, we will discuss how we can leverage MLflow with these tools and techniques to analyze how our search is performing and to productionize the best models.
Speaker: Joseph Bradley
GPT-2: Language Models are Unsupervised Multitask LearnersYoung Seok Kim
Review of paper
Language Models are Unsupervised Multitask Learners
(GPT-2)
by Alec Radford et al.
Paper link: https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf
YouTube presentation: https://youtu.be/f5zULULWUwM
(Slides are written in English, but the presentation is done in Korean)
This slide deck provides a survey of research in the field of coreference resolution. We survey 10 significant research papers and also provide a detailed description of the problem and also suggest future research directions.
Apply chinese radicals into neural machine translation: deeper than character...Lifeng (Aaron) Han
LPRC 2018: Limerick Postgraduate Research Conference
Lifeng Han and Shaohui Kuang. 2018. Apply Chinese radicals into neural machine translation: Deeper than character level. ArXiv pre-print https://arxiv.org/abs/1805.01565v1
Webinar at AgileTD Mondays: Mind maps to support exploratory testing: a team ...Claudia Badell
This webinar is about how mind maps are used to support exploratory testing in a cross-functional team. Claudia will share how mind maps help the team to have a common understanding of what to test, and how mind maps are designed by the team in a way that they can easily be read and understood regardless who created them. She will also present how mind maps are re-used through the different releases. At the end of the webinar, Claudia will share what they have learned as a team when applying this testing strategy.
This story is set during the process of building a multi-platform UI prototyping tool mainly for interaction designers. The team, fully dedicated to building the product, consists of highly qualified and experienced professionals: developers (7), interaction designers (1), visual designers (1), technical writers (1), and testers (1).
Duration: 20 minutes
Webinar at AgileTD Mondays: Mind maps to support exploratory testing: a team ...
CO620
1. CORPORA-BASED GENERATION OF
DEPENDENCY PARSER MODELS FOR
NATURAL LANGUAGE PROCESSING
by Edmond Lepedus
supervised by Marek Grześ, Christian Kissig and Laura Bocchi
10. Stanford CoreNLP
• Free, open-source NLP toolkit
• Includes a dependency parser backed by a neural
network classifier
11. Stanford CoreNLP
• Free, open-source NLP toolkit
• Includes a dependency parser backed by a neural
network classifier
• Parses 1000 sentences per second at 92.2% accuracy:
12. Stanford CoreNLP
• Free, open-source NLP toolkit
• Includes a dependency parser backed by a neural
network classifier
• Parses 1000 sentences per second at 92.2% accuracy:
13. Stanford CoreNLP
• Free, open-source NLP toolkit
• Includes a dependency parser backed by a neural
network classifier
• Parses 1000 sentences per second at 92.2% accuracy:
• Trained on manually annotated text
20. Motivation
• Decrease the cost of training data
• Increase the availability of training data
• Increase parsing accuracy
21. Motivation
• Decrease the cost of training data
• Increase the availability of training data
• Increase parsing accuracy
• Enable the parsing of languages with few
remaining speakers
26. Overview
1. Create a ‘blank’ model
2. Parse corpus with model & log decisions
3. Extract heuristics from corpus & parse log
27. Overview
1. Create a ‘blank’ model
2. Parse corpus with model & log decisions
3. Extract heuristics from corpus & parse log
4. Generate training examples by modifying the
logged decisions to fit the discovered heuristics
28. Overview
1. Create a ‘blank’ model
2. Parse corpus with model & log decisions
3. Extract heuristics from corpus & parse log
4. Generate training examples by modifying the
logged decisions to fit the discovered heuristics
5. Train model on new examples
29. Diagram
Create a ‘blank’ model
Parse & log
Extract heuristics
Generate training examples
Train new model
59. Conclusion
• We modified the Stanford CoreNLP toolkit to
enable the creation of ‘blank’ parser models
60. Conclusion
• We modified the Stanford CoreNLP toolkit to
enable the creation of ‘blank’ parser models
• We developed a workflow for training parser
models without using annotated corpora
61. Conclusion
• We modified the Stanford CoreNLP toolkit to
enable the creation of ‘blank’ parser models
• We developed a workflow for training parser
models without using annotated corpora
• We showed that this quickly yields qualitative
improvements in parser outputs over the ‘blank’
models
62. Conclusion
• We modified the Stanford CoreNLP toolkit to
enable the creation of ‘blank’ parser models
• We developed a workflow for training parser
models without using annotated corpora
• We showed that this quickly yields qualitative
improvements in parser outputs over the ‘blank’
models
• We proposed three avenues for further research
64. REFERENCES
[1] C. Manning, M. Surdeanu, J. Bauer, J. Finkel, S. Bethard, and D. McClosky,
“The Stanford CoreNLP Natural Language Processing Toolkit,” presented at the
Proceedings of 52nd Annual Meeting of the Association for Computational
Linguistics: System Demonstrations, Stroudsburg, PA, USA, 2014, pp. 55–60.
[2] J. Nivre, “Dependency Parsing,” vol. 4, no. 3, pp. 138–152, Mar. 2010.
[3] D. Chen and C. D. Manning, “A Fast and Accurate Dependency Parser
using Neural Networks.,” EMNLP, pp. 740–750, 2014.
[4] D. Jurafsky and J. H. Martin, Speech and language processing: an
introduction to natural language processing, computational linguistics, and
speech recognition. Upper Saddle River, NJ: Prentice-Hall, 2000.