cdec: A Decoder, Alignment, and Learning Framework for Finite- State and Context-Free Translation Models

By Chris Dyer, Adam Lopez, Juri Ganitkevitch, Jonathan Weese, Ferhan Ture, Phil Blunsom, Hendra Setiawan, Vladimir Eidelman, Philip Resnik. 2010

254 citations recorded by the source corpus.

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Parallel Corpus Filtering via Pre-trained Language Models (2020, background): “Denkowski et al. (2012), Dyer et al. (2010) and Heaﬁeld (2011) use language models and word alignments to determine how likely sentences are to be a good translation of another.”
Recurrent Continuous Translation Models (2013, methodology): “The performance of the RCTM probabilities joined with a single word penalty feature matches the performance of the state-of-the-art translation system cdec that makes use of twelve features including five alignment-based translation models (Dyer et al., 2010).”
OpenNMT: Open-Source Toolkit for Neural Machine Translation (2017, background): “Just as the SMT community benefited greatly from toolkits like Moses (Koehn et al., 2007) for phrase-based SMT and CDec (Dyer et al., 2010) or travatar (Neubig, 2013) for syntax-based SMT, NMT toolkits can provide a foundation to build upon.”
Addressing the Rare Word Problem in Neural Machine Translation (2014, background): “Standard phrasebased systems (Koehn et al., 2007; Chiang, 2007; Cer et al., 2010; Dyer et al., 2010), on the other hand, do not suffer from the rare word problem to the same extent because they can support a much larger vocabulary, and because their use of explicit alignments and phrase tables allow”
Grid Long Short-Term Memory (2015, methodology): “Test CDEC [8] 50.1 58.9 Reference Generated thankyou. pleasepayforthisbillatthecashier. thankyou,ma’am. pleasegivethisbilltothecashierandpaythere. howabouthavinglunchwithmesomeday? ifoundagoodrestaurantnearmyhotel. howaboutlunchwithme? ifoundagoodrestaurantnearmyhotel.”
Improving Vector Space Word Representations Using Multilingual Correlation (2014, methodology): “We got these word alignment counts using cdec (Dyer et al., 2010) from the parallel news commentary corpora (WMT 2006-10) combined with the Europarl corpus for English{German, French, Spanish}.”
Zipporah: a Fast and Scalable Data Cleaning System for Noisy Web-Crawled Parallel Corpora (2017, background): “The qeclean system (Denkowski et al., 2012; Dyer et al., 2010; Heafield, 2011) uses word alignments and language models to select sentence pairs that are likely to be good translations of one another.”
A Shared Task on Multimodal Machine Translation and Crosslingual Image Description (2016, methodology): “The cdec decoder (Dyer et al., 2010) was used to produce hypothesis lists, which were re-scored by comparison with similar image captions from the training corpus using the pivoting approach described in Hitschler et al.”
Compositional Morphology for Word Representations and Language Modelling (2014, methodology): “We use cdec (Dyer et al., 2010; 2013) to build symmetric word-alignments and extract rules for hierarchical phrase-based translation (Chiang, 2007).”
Multilingual Models for Compositional Distributed Semantics (2014, methodology): “We use the cdec decoder (Dyer et al., 2010) (Collobert et al., 2011) and Polyglot (Al-Rfou’ et al., 2013).”
Sheffield Systems for the Finnish-English WMT Translation Task (2015, methodology): “In this paper we presented our submission, which was produced from a system built using the CDEC decoder.”
The CMU Machine Translation Systems at WMT 2014 (2014, methodology): “The decoder infrastructure we used was cdec (Dyer et al., 2010).”
Learning to Represent Words in Context with Multilingual Supervision (2015, methodology): “We trained our baseline system with cdec (Dyer et al., 2010) and obtained synchronous context-free grammars rules to translate sentences.”
Class-based N-gram language difference models for data selection (2015, methodology): “We trained all SMT systems using cdec [15], tuned with MIRA [16].”
Learning Structured Predictors from Bandit Feedback for Interactive NLP (2016, methodology): “(2015) is our use of the SCFG decoder cdec (Dyer et al., 2010) (instead of the phrase-based Moses decoder).”
Phrasal: A Toolkit for New Directions in Statistical Machine Translation (2014, background): “, 2012), cdec (Dyer et al., 2010) and the first version of our package, Phrasal (Cer et al.”