 | Statistical Machine Translation Group at the University of Edinburgh |
There are many people here in Edinburgh working on statistical machine translation. This group meets once a week to exchange ideas, discuss research, or review work in the field. The format is informal.
The meetings will take place Wednesdays at 3pm in room 4.02, unless otherwise noted. Questions should be directed to statmt@inf.
Feb 3: Oliver Wilson on distributed language models.
| 2009 | |
|---|---|
| Jan 20 | Abby Levenberg report on JHU project |
| Dec 15 | A Hierarchical Bayesian Language Model Based On Pitman-Yor Processes by Yee Whye Teh; and Interpolating Between Types and Tokens by Estimating Power-Law Generators by Sharon Goldwater et al. (also see A parallel training algorithm for hierarchical Pitman-Yor process language models by Songfang Huang and Steve Renals) |
| Dec 1 | NAACL abstract critiques. See also: Simon Peyton Jones' advice on How to write a research paper |
| Nov 24 | Lexi - Bayesian Inference with Tears by Kevin Knight |
| Nov 17 | Hieu: more adventures with Moses, and Joint Decoding with Multiple Translation Models by Liu et al. |
| Nov 10 | Adam: Semiring Parsing |
| Nov 3 | Abhishek: All about non-local features and incorporating them into models efficiently. A Smorgasbord of Features for Statistical Machine Translation by Och et al.; Forest Reranking: Discriminative Parsing with Non-Local Features. by Liang Huang; and Incorporating Non-local Information Into Information Extraction Systems By Gibbs Sampling by Finkel et al. |
| Oct 27 | forest-based concensus and MBR algorithms: Fast Concensus Decoding over Translation Forests by John DeNero, David Chiang, & Kevin Knight (ACL 2009); and Efficient Minimum Error Rate Training and Minimum Bayes-Risk Decoding for Translation Hypergraphs and Lattices by Shankar Kumar, Wolfgang Macherey, Chris Dyer, & Franz Och (ACL 2009) |
| Oct 20 | Hierarchical Phrase-based Translation by David Chiang |
| 13 Oct | Anoop Sarkar: Active Learning for Multilingual Statistical Machine Translation (work with Reza Haffari) |
| 6 Oct | Philip Williams: Towards Statistical Translation with Unification Grammars (Master thesis report) |
| 29 Sep | Philipp Koehn: Interactive Assistance to Human Translators using Statistical Machine Translation Methods (software). |
| 22 Sep | Soft Syntactic Constraints for Word Alignment through Discriminative Training by Colin Cherry & Dekang Lin; and Better Word Alignments with Supervised ITG Models by Aria Haghighi, John Blitzer and Dan Klein |
| 15 Sep | Quadratic-Time Dependency Parsing for Machine Translation, Michel Galley & Christopher Manning; and A Syntactified Direct Translation Model with Linear-time Decoding by Hany Hassan, Khalil Sima'an and Andy Way |
| 8 Sep | Michael Auli: Tree-to-String Alignment Models (ISI internship project). Also: MT Summit / NIST postmortem |
| 1 Sep | no meeting |
| 25 Aug | Learning Linear Ordering Problems for Better Translation, by Roy Tromble & Jason Eisner; and Sinuhe -- Statistical Machine Translation using a Globally Trained Conditional Exponential Family Translation Model by Matti Kääriäinen |
| 18 Aug | Phrase-Based Statistical Machine Translation as a Traveling Salesman Problem by Mikhail Zaslavskiy; Marc Dymetman; Nicola Cancedda |
| 11 Aug | ACL overview |
| 4 Aug | Visiting students (Andreas Zollmann and Juri Ganitkevitch) talk about their work |
| 28 Jul | Quasi-Synchronous Grammars: Alignment by Soft Projection of Syntactic Dependencies by David A. Smith & Jason Eisner; and Feature-Rich Translation by Quasi-Synchronous Lattice Parsing, by Kevin Gimpel & Noah Smith |
| 21 Jul | Synchronous Tree Adjoining Machine Translation, by Steve DeNeefe & Kevin Knight |
| 14 Jul | Graph-based Learning for Statistical Machine Translation by Andrei Alexandrescu & Katrin Kirchhoff |
| 7 Jul | Efficient Parsing for Transducer Grammars by John DeNero, Mohit Bansal, Adam Pauls and Dan Klein; and Faster MT Decoding Through Pervasive Laziness, by Michael Pust & Kevin Knight |
| 30 Jun | First- and Second-Order Expectation Semirings with Applications to Minimum-Risk Training on Translation Forests by Zhifei Li & Jason Eisner |
| 23 Jun | Feasibility of Human-in-the-loop Minimum Error Rate Training by Omar Zaidan & Chris Callison-Burch; and Cube Pruning as Heuristic Search by Mark Hopkins and Greg Langmead |
| 16 Jun | NAACL Post-mortem |
| 9 Jun | No meeting |
| 2 Jun | No meeting - NAACL |
| 26 May | A Gibbs Sampler for Phrasal Synchronous Grammar Induction by Phil Blunsom, Trevor Cohn, Chris Dyer and Miles Osborne |
| 19 May | Unsupervised Multilingual Grammar Induction, Benjamin Snyder, Tahira Naseem and Regina Barzilay; and the paper from Philipp's email |
| 12 May | Parsers as language models for statistical machine translation by Matt Post, and Daniel Gildea; and Variational Decoding for Statistical Machine Translation by Zhifei Li, Jason Eisner and Sanjeev Khudanpur |
| 5 May | Preference Grammars: Softening Syntactic Constraints to Improve Statistical Machine Translation, Ashish Venugopal, Andreas Zollmann, Noah A. Smith, and Stephan Vogel; and Online EM for unsupervised models by Percy Liang and Dan Klein |
| 28 Apr | 11,001 new features for statistical machine translation, David Chiang, Kevin Knight, and Wei Wang; and Streaming for large scale NLP: Language Modeling , Amit Goyal, Hal Daume III, and Suresh Venkatasubramanian |
| 21 Apr | Gibbs sampling in phrase-based machine translation |
| 14 Apr | Correcting Automatic Translations through Collaborations between MT and Monolingual Target Language Users by Joshua Albrecht, Rebecca Hwa and G. Elisabeta Marai; and Cube Summing, Approximate Inference with Non-Local Features, and Dynamic Programming without Semirings by Kevin Gimpel and Noah A. Smith |
| 7 Apr | No meeting |
| 31 Mar | No meeting - EACL |
| 24 Mar | Chris Dyer - NAACL talk |
| 17 Mar | Hieu Hoang - Hierarchical Moses |
| 10 Mar | Adam Lopez - EACL Practice talk |
| 3 Mar | WMT09 Shared Task Discussion |
| 24 Feb | Michael Auli - EACL Practice talk |
| 17 Feb | Context-dependent alignment models for statistical machine translation. by J. Brunning, A. de Gispert, and W. Byrne. |
| 10 Feb | Two Languages are Better than One (for Syntactic Parsing) by David Burkett and Dan Klein; and Hierarchical phrase-based translation with weighted finite state transducers. by G. Iglesias Iglesias, A. de Gispert, E. R. Banga, and W. Byrne. |
| 3 Feb | TransSearch: What are translators looking for? by Elliott Macklovitch, Guy Lapalme and Fabrizio Gotti; and A Simple and Effective Hierarchical Phrase Reordering Model by Michel Galley and Christopher D. Manning |
| 27 Jan | No meeeting - MT Marathon |
| 20 Jan | Sampling Alignment Structure under a Bayesian Translation Model by John DeNero, Alexandre Bouchard-Côté and Dan Klein; Language and Translation Model Adaptation using Comparable Corpora by Matthew Snover, Bonnie Dorr and Richard Schwartz |
| 2008 | |
| 25 Nov | Lattice Minimum Bayes-Risk Decoding for Statistical Machine Translation by Roy Tromble and Shankar Kumar and Franz Och and Wolfgang Macherey; Lattice-based Minimum Error Rate Training for Statistical Machine Translation by Wolfgang Macherey and Franz Och and Ignacio Thayer and Jakob Uszkoreit |
| 18 Nov | Decomposability of Translation Metrics for Improved Evaluation and Efficient Algorithms by David Chiang Steve DeNeefe, Yee Seng Chan and Hwee Tou Ng and Syntactic Models for Structural Word Insertion and Deletion during Translation by Arul Menezes and Chris Quirk |
| 11 Nov | Abby Levenberg First Year Report |
| 4 Nov | EMNLP debrief, report from Eva Hasler on maxent based reordering |
| 28 Oct | No meeting - EMNLP |
| 21 Oct | No meeting - EMNLP |
| 14 Oct | Dry run of EMNLP paper: Probabilistic Inference for Machine Translation with Millions of Sparse Features and a Language Model by Phil Blunsom and Miles Osborne |
| 7 Oct | Research update from Abhishek and Online Large-Margin Training of Syntactic and Structural Translation Features by David Chiang, Yuval Marton and Philip Resnik |
| 30 Sep | Coarse-to-Fine Syntactic Machine Translation using Language Projections by Slav Petrov, Aria Haghighi and Dan Klein |
| 23 Sep | Introductions from the new PhD students and Extracting synchronous grammar rules from word-level alignments in linear time by Hao Zhang, Daniel Gildea and David Chiang |
| 16 Sep | Reading the Markets: Forecasting Public Opinion of Political Candidates by News Analysis by Kevin Lerman, Ari Gilder, Mark Dredze and Fernando Pereira and Linguistically Annotated BTG for Statistical Machine Translation by Deyi Xiong, Min Zhang, Aiti Aw and Haizhou Li |
| 9 Sep | No meeting - IRTG summer school talks today |
| 2 Sep | Regenerating Hypotheses for Statistical Machine Translation by Boxing Chen, Min Zhang, Aiti Aw and Haizhou Li and Phrasal segmentation models for statistical machine translation by Graeme Blackwood, Adrià de Gispert and William Byrne |
| 26 Aug | Coling post-mortem |
| 19 Aug | No meeting - Coling |
| 12 Aug | Getting the Structure Right for Word Alignment: LEAF by Alex Fraser and Daniel Marcu; and The Complexity of Phrase Alignment Problems by John DeNero and Dan Klein |
| 5 Aug | Bayesian Learning of Non-Compositional Phrases with Synchronous Parsing by Hao Zhang and Chris Quirk and Robert C. Moore and Daniel Gildea |
| 29 Jul | A Systematic Comparison of Phrase-Based, Hierarchical and Syntax-Augmented Statistical MT. by Andreas Zollmann, Ashish Venugopal, Franz Och and Jay Ponte; and Generalizing Word Lattice Translation by Christopher Dyer, Smaranda Muresan, Philip Resnik |
| 22 Jul | Grishma Govani will be talking about her work on English-Hindi translation and we'll be discussing Name Translation in Statistical Machine Translation - Learning When to Transliterate by Ulf Hermjakob, Kevin Knight and Hal Daumé III |
| 15 Jul | Distributed Word Clustering for Large Scale Class-Based Language Modeling in Machine Translation by Jakob Uszkoreit & Thorsten Brants and Randomized Language Models via Perfect Hash Functions by David Talbot & Thorsten Brants |
| 1 Jul | A New String-to-Dependency Machine Translation Algorithm with a Target Dependency Language Model by Libin Shen, Jinxi Xu, Ralph Weischedel and Cohesive Phrase-Based Decoding for Statistical Machine Translation by Colin Cherry |
| 25 Jun | Lexi Birch: Multiple Reorderings in Phrase-Based Machine Translation by Niyu Ge, Abe Ittycheriah, Kishore Papineni and Syntactic Reordering Integrated with Phrase-Based SMT by Jakob Elming |
| 2007 | |
| 2 Oct | Phil Blunsom: Generative Models of Noisy Translations with Applications to Parallel Fragment Extraction by Chris Quirk, Raghavendra Udupa U., Arul Menezes |
| 25 Sep | Group meeting |
| 18 Sep | Trevor Cohn: Unsupervised Estimation for Noisy-Channel Models by M. Mylonakis, K. Sima'an and R. Hwa (ICML 2007) |
| 4 Sep | Philipp Koehn: Improved Word-Level System Combination for Machine Translation by Antti-Veikko I. Rosti and Spyros Matsoukas and Richard Schwartz (ACL 2007); Lefteris Avramidis: Enriching Input in Statistical Machine Translation, MSc project |
| 28 Aug | Alexandra Birch: The impact of parse quality on syntactically-informed statistical machine translation by Chris Quirk and Simon Corston-Oliver (EMNLP 2006) |
| 21 Aug | Group meeting |
| 7 Aug | Trevor Cohn: Improving Word Alignment with Bridge Languages by Shankar Kumar, Franz J. Och and Wolfgang Macherey (EMNLP 2007); Hieu Hoang: Deep Grammars in a Tree Labeling Approach to Syntax-based Statistical Machine Translation by Mark Hopkins and Jonas Kuhn (ACL 2007 Workshop on Deep Linguistic Processing) |
| 31 Jul | Josh Schroeder: Computing Consensus Translation from Multiple Machine Translation Systems Using Enhanced Hypotheses Alignment by Evgeny Matusov, Nicola Ueffing, Hermann Ney (EACL 2006) and Computing Consensus Translation from Multiple Machine Translation Systems by Srinivas Bangalore, German Bordel, Giuseppe Riccardi (ASRU 2001); Lefteris Avramidis: Improving Statistical Machine Translation Using Word Sense Disambiguation by Marine Carpuat and Dekai Wu (EMNLP 2007) |
| 24 Jul | Phil Blunsom: Forest Rescoring: Faster Decoding with Integrated Language Models by Liang Huang and David Chiang (ACL 2007); Miles Osborne: Continuous Space Language Models for Statistical Machine Translation by Holger Schwenk, Daniel Dechelotte, Jean-Luc Gauvain (ACL 2006) |
| 17 Jul | Alexandra Birch: Improving Translation Quality by Discarding Most of the Phrasetable by Johnson et al (EMNLP 2007); Trevor Cohn: Online Large-Margin Training for Statistical Machine Translation by Taro Watanabe, Jun Suzuki, Hajime Tsukada and Hideki Isozaki (EMNLP 2007) |
| 19 Jun | Alexandra Birch: Inversion Transduction Grammar for Joint Phrasal Translation Modeling by Colin Cherry, Dekang Lin (NAACL 2007) and A Discriminative Syntactic Word Order Model for Machine Translation by Pi-Chuan Chang, Kristina Toutanova (ACL 2007) |
| 12 Jun | Josh Schroeder: A Re-examination of Machine Learning Approaches for Sentence-Level MT Evaluation by Joshua Albrecht and Rebecca Hwa and Regression for Sentence-Level MT Evaluation with Pseudo References by Joshua Albrecht and Rebecca Hwa (ACL 2007) |
| 5 Jun | Miles Osborne: Transductive learning for statistical machine translation by Nicola Ueffing, Gholamreza Haffari and Anoop Sarkar (ACL 2007) |
| 22 May | Hieu Hoang: Chunk-Level Reordering of Source Language Sentences with Automatically Learned Rules for Statistical Machine Translation by Yuqi Zhang, Richard Zens, Hermann Ney (NAACL 2007); Abhishek Arun: A Log-Linear Block Transliteration Model based on Bi-Stream HMMs by Bing Zhao; Nguyen Bach; Ian Lane; Stephan Vogel (NAACL 2007) |
| 15 May | Phil Blunsom: Kernel Regression Based Machine Translation by Zhuoran Wang, John Shawe-Taylor, Sandor Szedmak (NAACL 2007); Miles Osborne: Combining Outputs from Multiple Machine Translation Systems by Antti-Veikko Rosti, Necip Fazil Ayan, Bing Xiang, Spyros Matsoukas, Richard Schwartz, Bonnie Dorr (NAACL 2007) |
| 10 May | Alexandra Birch: Direct Translation Model 2 by Abraham Ittycheriah and Salim Roukos (NAACL 2007); Trevor Cohn: Source-Language Features and Maximum Correlation Training for Machine Translation Evaluation by Ding Liu, Daniel Gildea (NAACL 2007) |
| 24 Apr | Group meeting |
| 13 Mar | Philipp Koehn: Factored translation results |
| 2006 | |
| 12 Jul | ACL 2006 Paper: Trevor Cohn: An End-to-End Discriminative Approach to Machine Translation by P. Liang, Alexandre Bouchard-Cote, D. Klein and B. Taskar |
| 28 Jun | Planning meeting for NIST Eval |
| 30 May | NAACL 2006 Paper: Alexandra Birch: Synchronous Binarization for Machine Translation by Hao Zhang, Lian Huang, Daniel Gildea and Kevin Knight |
| 23 May | NAACL 2006 Paper: Chris Callison-Burch: Paraphrasing for Automatic Evaluation by David Kauchak and Regina Barzilay |
| 16 May | WMT06 Paper: Alexandra Birch: Why Generative Phrase Models Underperform Surface Heuristics by John DeNero, Dan Gillick, James Zhang and Dan Klein |
| 10 May | WMT06 Papers: Chris Callison-Burch: "Contextual Bitext-Derived Paraphrases in Automatic MT Evaluation" by Karolina Owczarzak, Declan Groves, Josef Van Genabith and Andy Way; Trevor Cohn: "N-Gram Posterior Probabilities for Statistical Machine Translation" by Richard Zens and Hermann Ney; Abhishek Arun: "Syntax Augmented Machine Translation via Chart Parsing" by Andreas Zollmann and Ashish Venugopal |
| 4 May | Philipp Koehn: Manual and Automatic MT Evaluation |
| 25 Apr | Chris Callison-Burch: Grammatical Machine Translation by Stefan Riezler and John Maxwell. Hieu Hoang: Progress on Moses. |
| 18 Apr | Philipp Koehn: "Computing Consensus Translation from Multiple Machine Translation Systems Using Enhanced Hypotheses Alignment" (EACL06) by Evgeny Matusov, Nicola Ueffing, Hermann Ney. Chris Callison-Burch: "A Comparison of Syntactically Motivated Word Alignment Spaces" (EACL06) by Colin Cherry, Dekang Lin |
| 11 Apr | Philipp Koehn: Research in the GALE program |
| 4 Apr | Amittai Axelrod: Report from TC-STAR OpenLab 2006 workshop (program) |
| 14 Mar | David Talbot: Recent research on reducing redundant morphology |
| 7 Mar | Review of Research in the AGILE consortium |
| 21 Feb | "An Empirical Study of Smoothing Techniques for Language Modeling", by Stanley Chen and Joshua Goodman |
| 14 Feb | Philipp Koehn: Introduction to Smoothing in Language Models |
| 7 Feb | "Phrase-Based Backoff Models for Machine Translation of Highly Inflected Languages" by Mei Yang and Kathrin Kirchhoff |
| 24 Jan | Group Meeting |
| 10 Jan | Group Meeting |
| 2005 | |
| 12 Dec | Abhishek Arun: Minimum Error Rate Training for Statistical Machine Translation by Franz Och and Considerations in Maximum Mutual Information and Minimum Classification Error Training for Statistical Machine Translation by Ashish Venugopal, Stephan Vogel |
| 5 Dec | David Talbot: "Improving Statistical MT through Morphological Analysis" by Sharon Goldwater and David McClosky and "Automatic Discovery of Non-Compositional Compounds in Parallel Data", by Dan Melamed |
| 28 Nov | Group Meeting |
| 21 Nov | Group Meeting |
| 7 Nov | Amittai Axelrod: "Clustered Language Models based on Regular Expressions for SMT", by Sasa Hasan and Hermann Ney |
| 30 Oct | Philipp Koehn: I will share some impressions from the IWSLT workshop. |
| 13 Sep | Chris Callison-Burch: "BLANC: Learning Evaluation Metrics for MT", by Lucian Vlad Lita, Monica Rogati and Alon Lavie (CMU) |
| 6 Sep | Planning Meeting |
| 30 Aug | Philipp Koehn: "Local Phrase Reordering Models for Statistical Machine Translation", by Shankar Kumar and William Byrne |
| 26 Jul | Amittai Axelrod, David Talbot: "Novel Reordering Approaches In Phrase-Based Statistical Machine Translation", by S. Kanthak, D. Vilar, E. Matusov, R. Zens, and H. Ney "Reordering Constraints for Phrase-Based Statistical Machine Translation", by R. Zens, H. Ney, T. Watanabe, and E. Sumita |
| 19 Jul | Philipp Koehn: a second look at: "Dependency Tree Translation: Syntactically Informed Phrasal SMT", Chris Quirk, Arul Menezes, Colin Cherry MSR Report |
| 12 Jul | Amittai Axelrod: Ongoing work for Master thesis |
| 5 Jul | Philipp Koehn: Lessons from NIST MT Eval 2005, Inspirations from ACL 2005 |
| 14 Jun | Amittai Axelrod, Alexandra Birch Mayne, David Talbot: ACL papers "Dependency Treelet Translation: Syntactically Informed Phrasal SMT", Chris Quirk, Arul Menezes and Colin Cherry "Log-linear Models for Word Alignment", Yang Liu, Qun Liu and Shouxun Lin "A Localized Prediction Model for Statistical Machine Translation", Christoph Tillmann and Tong Zhang |
| 7 Jun | Chris Callison-Burch: Linear-B Open Source Initiative |
| 24 May | Amittai Axelrod: ACL Paper "A Hierachical Phrase-Based Model for Statistical Machine Translation", David Chiang. |
| 17 May | Group Meeting Reflections on NIST MT Eval 2005 |
| 10 May | Group Meeting NIST MT Eval 2005 Progress |
| 3 May | Group Meeting NIST MT Eval 2005 Progress |
| 26 Apr | Group Meeting NIST MT Eval 2005 Progress |
| 19 Apr | Group Meeting NIST MT Eval 2005 Progress |
| 12 Apr | Group Meeting NIST MT Eval 2005 Progress |
| 5 Apr | Philipp Koehn: Reranking and Minimum Error Rate Training |
| 29 Mar | Philipp Koehn: Challenges in Arabic-English MT |
| 22 Mar | Philipp Koehn: Issues in Preprocessing |
| 15 Mar | Philipp Koehn: Baseline System Performance |
| 8 Mar | Philipp Koehn: DARPA MT Eval 2005 This and the following sessions will focus on a group effort to do well in the upcoming DARPA MT Eval competition. More public meetings will be announced. |
| 1 Mar | Philipp Koehn: Intro to my Phrase-Based MT System. This will be a more practical walk-through session to learn everything about Pharaoh. |
| 23 Feb | Philipp Koehn: Intro to my Phrase-Based MT System. I give an overview of my machine translation system as it currently works. I cover both the theory (what is going on?) and the practice (how do I get it to run?). |
| 16 Feb | Planning Meeting |