Task Alternation in Parallel Sentence Retrieval for Twitter Translation

We present an approach to mine comparable data for parallel sentences using translation-based cross-lingual information retrieval (CLIR). By iteratively alternating between the tasks of retrieval and translation, an initial general-domain model is allowed to adapt to in-domain data. Adaptation is done by training the translation system on a few thousand sentences retrieved in the step before. Our setup is time- and memory-efficient and of similar quality as CLIR-based adaptation on millions of parallel sentences.

[1]  Dragos Stefan Munteanu,et al.  Improving Machine Translation Performance by Exploiting Non-Parallel Corpora , 2005, CL.

[2]  S. T. Buckland,et al.  Computer-Intensive Methods for Testing Hypotheses. , 1990 .

[3]  Jinxi Xu,et al.  Evaluating a probabilistic model for cross-lingual information retrieval , 2001, SIGIR '01.

[4]  Hermann Ney,et al.  A Systematic Comparison of Various Statistical Alignment Models , 2003, CL.

[5]  Jimmy J. Lin,et al.  Looking inside the box: context-sensitive translation for cross-language information retrieval , 2012, SIGIR '12.

[6]  Stephen E. Robertson,et al.  Okapi at TREC-7: Automatic Ad Hoc, Filtering, VLC and Interactive , 1998, TREC.

[7]  Marcello Federico,et al.  Domain Adaptation for Statistical Machine Translation with Monolingual Resources , 2009, WMT@EACL.

[8]  David Chiang,et al.  Hierarchical Phrase-Based Translation , 2007, CL.

[9]  Philipp Koehn,et al.  Experiments in Domain Adaptation for Statistical Machine Translation , 2007, WMT@ACL.

[10]  Jimmy J. Lin,et al.  Combining Statistical Translation Techniques for Cross-Language Information Retrieval , 2012, COLING.

[11]  Stefan Riezler,et al.  Twitter Translation using Translation-Based Cross-Lingual Retrieval , 2012, WMT@NAACL-HLT.

[12]  Vladimir Eidelman,et al.  cdec: A Decoder, Alignment, and Learning Framework for Finite- State and Context-Free Translation Models , 2010, ACL.

[13]  Stefan Riezler,et al.  On Some Pitfalls in Automatic Evaluation and Significance Testing for MT , 2005, IEEvaluation@ACL.

[14]  K. J. Evans,et al.  Computer Intensive Methods for Testing Hypotheses: An Introduction , 1990 .

[15]  Dragos Stefan Munteanu,et al.  Extracting Parallel Sub-Sentential Fragments from Non-Parallel Corpora , 2006, ACL.

[16]  Jakob Uszkoreit,et al.  Large Scale Parallel Document Mining for Machine Translation , 2010, COLING.

[17]  Anne Lohrli.  Chapman and Hall , 1985 .

[18]  Holger Schwenk,et al.  On the Use of Comparable Corpora to Improve SMT performance , 2009, EACL.

[19]  Robert L. Mercer,et al.  The Mathematics of Statistical Machine Translation: Parameter Estimation , 1993, CL.

[20]  Timothy Baldwin,et al.  langid.py: An Off-the-shelf Language Identification Tool , 2012, ACL.

[21]  Chin-Yew Lin,et al.  ORANGE: a Method for Evaluating Automatic Evaluation Metrics for Machine Translation , 2004, COLING.

[22]  Steven Abney,et al.  Semisupervised Learning for Computational Linguistics , 2007 .

[23]  Jimmy J. Lin,et al.  Why Not Grab a Free Lunch? Mining Large Corpora for Parallel Sentences to Improve Translation Modeling , 2012, NAACL.

[24]  Richard M. Schwartz,et al.  Language and Translation Model Adaptation using Comparable Corpora , 2008, EMNLP.