Title | ||
---|---|---|
Joshua 2.0: a toolkit for parsing-based machine translation with syntax, semirings, discriminative training and other goodies |
Abstract | ||
---|---|---|
We describe the progress we have made in the past year on Joshua (Li et al., 2009a), an open source toolkit for parsing based machine translation. The new functionality includes: support for translation grammars with a rich set of syntactic nonterminals, the ability for external modules to posit constraints on how spans in the input sentence should be translated, lattice parsing for dealing with input uncertainty, a semiring framework that provides a unified way of doing various dynamic programming calculations, variational decoding for approximating the intractable MAP decoding, hypergraph-based discriminative training for better feature engineering, a parallelized MERT module, documentlevel and tail-based MERT, visualization of the derivation trees, and a cleaner pipeline for MT experiments. |
Year | Venue | Keywords |
---|---|---|
2010 | WMT@ACL | input uncertainty,parsing-based machine translation,input sentence,variational decoding,better feature engineering,translation grammar,intractable map decoding,machine translation,discriminative training,tail-based mert,parallelized mert module,mt experiment |
Field | DocType | Citations |
Rule-based machine translation,Computer science,Visualization,Machine translation,Feature engineering,Transfer-based machine translation,Natural language processing,Artificial intelligence,Parsing,Discriminative model,Syntax | Conference | 14 |
PageRank | References | Authors |
0.99 | 19 | 11 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhifei Li | 1 | 339 | 23.83 |
Chris Callison-Burch | 2 | 4872 | 259.75 |
chris dyer | 3 | 5438 | 232.28 |
Juri Ganitkevitch | 4 | 659 | 32.71 |
Ann Irvine | 5 | 219 | 15.23 |
Sanjeev Khudanpur | 6 | 2155 | 202.00 |
Lane Schwartz | 7 | 209 | 18.01 |
Wren N. G. Thornton | 8 | 124 | 7.74 |
Ziyuan Wang | 9 | 131 | 13.42 |
Jonathan Weese | 10 | 325 | 19.11 |
Omar Zaidan | 11 | 787 | 43.28 |