Columbia SMT reading group
We are starting a Statistical Machine Translation reading group this semester to discuss recent work in the field, focusing in particular (but not exclusively) on syntax for SMT. All are welcome!
We meet on alternate tuesdays from 11am to 12pm (see schedule below), in the CCLS conference room (Room 850, Interchurch Center)
Schedule
| Date | Paper(s) | Presenter |
| Sep 29 | Learning Linear Ordering Problems for Better Translation, Roy Tromble and Jason Eisner (EMNLP 2009) | |
| Oct 13 | Improved Word Alignment with Statistics and Linguistic Heuristics, Ulf Hermjakob (EMNLP 2009) | Kristen Parton |
| Oct 27 | Syntactic Phrase Reordering for English-to-Arabic Statistical Machine Translation, Ibrahim Badr, Rabih Zbib and James Glass (EACL 09) | Ahmed El Kholy |
| Nov 10 | Quadratic-Time Dependency Parsing for Machine Translation, Michel Galley and Christopher D. Manning (ACL 2009) | Yves Scherrer |
Suggested papers
Here is a (very partial) list of papers that we can discuss. All suggestions are welcome (email marinex[at]xccls.columbia.edu)
Alignment
- Better Word Alignments with Supervised ITG Models, Aria Haghighi, John Blitzer, John DeNero and Dan Klein (ACL 2009)
- Context-dependent alignment models for statistical machine translation, Jamie Brunning, Adria de Gispert and William Byrne (HLT-NAACL 2009)
- Sampling Alignment Structure under a Bayesian Translation Model, John DeNero, Alexandre Bouchard-Cote and Dan Klein (EMNLP 2008)
MERT and other optimization methods
- 11,001 new features for statistical machine translation, David Chiang, Kevin Knight, and Wei Wang (HLT-NAACL 2009)
Decoding
- Variational Decoding for Statistical Machine Translation, Zhifei Li, Jason Eisner and Sanjeev Khudanpur
Global information for SMT
- Graph-based Learning for Statistical Machine Translation, Andrei Alexandrescu and Katrin Kirchhoff (HLT-NAACL 2009)
Textual entailment/paraphrasing/semantic roles for SMT
- Robust Machine Translation Evaluation with Entailment Features, Sebastian Pado, Michel Galley, Dan Jurafsky and Christopher D. Manning (ACL 2009)
- Source-Language Entailment Modeling for Translating Unknown Terms, Shachar Mirkin, Lucia Specia, Nicola Cancedda, Ido Dagan, Marc Dymetman and Idan Szpektor (ACL 2009)
- Improved Statistical Machine Translation Using Monolingually-Derived Paraphrases, Yuval Marton, Chris Callison-Burch and Philip Resnik (EMNLP 2009)
- Semantic Roles for SMT: A Hybrid Two-Pass Model, Dekai Wu and Pascale Fung (HLT-NAACL 2009)
Syntactic parsing (for MT)
- Quadratic-Time Dependency Parsing for Machine Translation, Michel Galley and Christopher D. Manning (ACL 2009)
- Unsupervised Multilingual Grammar Induction, Benjamin Snyder, Tahira Naseem and Regina Barzilay (ACL 2009)
- Two Languages are Better than One (for Syntactic Parsing), David Burkett and Dan Klein (EMNLP 2008)
Last updated: Sep 2009