Assessing quick update methods of statistical translation models

The ability to quickly incorporate incoming training data into a running translation system is critical in a number of applications. Mechanisms based on incremental model update and the online EM algorithm hold the promise of achieving this objective in a principled way. Still, efficient tools for incremental training are yet to be available. In this paper we experiment with simple alternative solutions for interim model updates, within the popular Moses system. Short of updating the model in real time, such updates can execute in short timeframes even when operating on large models, and achieve a performance level close to, and in some cases exceeding, that of batch retraining.

[1]  François Yvon,et al.  Towards contextual adaptation for any-text translation , 2012, IWSLT.

[2]  Roland Kuhn,et al.  Vector Space Model for Adaptation in Statistical Machine Translation , 2013, ACL.

[3]  Jianfeng Gao,et al.  Domain Adaptation via Pseudo In-Domain Data Selection , 2011, EMNLP.

[4]  Roland Kuhn,et al.  Discriminative Instance Weighting for Domain Adaptation in Statistical Machine Translation , 2010, EMNLP.

[5]  Andreas Stolcke,et al.  SRILM - an extensible language modeling toolkit , 2002, INTERSPEECH.

[6]  Chris Callison-Burch,et al.  A compact data structure for searchable translation memories , 2005, EAMT.

[7]  Philipp Koehn,et al.  Moses: Open Source Toolkit for Statistical Machine Translation , 2007, ACL.

[8]  Arianna Bisazza,et al.  Fill-up versus interpolation methods for phrase-based SMT adaptation , 2011, IWSLT.

[9]  Abby D. Levenberg,et al.  Stream-based statistical machine translation , 2011 .

[10]  Mauro Cettolo,et al.  WIT3: Web Inventory of Transcribed and Translated Talks , 2012, EAMT.

[11]  Daniel Jurafsky,et al.  Phrasal: A Statistical Machine Translation Toolkit for Exploring New Model Features , 2010, NAACL.

[12]  Roland Kuhn,et al.  Mixture-Model Adaptation for SMT , 2007, WMT@ACL.

[13]  Geoffrey E. Hinton,et al.  A View of the Em Algorithm that Justifies Incremental, Sparse, and other Variants , 1998, Learning in Graphical Models.

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

[15]  Chris Callison-Burch,et al.  Stream-based Translation Models for Statistical Machine Translation , 2010, NAACL.

[16]  Qun Liu,et al.  Improving Statistical Machine Translation Performance by Training Data Selection and Optimization , 2007, EMNLP-CoNLL.

[17]  Dan Klein,et al.  Online EM for Unsupervised Models , 2009, NAACL.

[18]  Francisco Casacuberta,et al.  Online Learning for Interactive Statistical Machine Translation , 2010, NAACL.

[19]  Hermann Ney,et al.  Improved Statistical Alignment Models , 2000, ACL.

[20]  Josef van Genabith,et al.  Domain Adaptation of Statistical Machine Translation using Web-Crawled Resources: A Case Study , 2012, EAMT.

[21]  George F. Foster,et al.  Batch Tuning Strategies for Statistical Machine Translation , 2012, NAACL.

[22]  Hermann Ney,et al.  HMM-Based Word Alignment in Statistical Translation , 1996, COLING.

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

[24]  Philipp Koehn,et al.  Europarl: A Parallel Corpus for Statistical Machine Translation , 2005, MTSUMMIT.

[25]  F ChenStanley,et al.  An Empirical Study of Smoothing Techniques for Language Modeling , 1996, ACL.

[26]  Stephan Vogel,et al.  Parallel Implementations of Word Alignment Tool , 2008, SETQALNLP.

[27]  O. Cappé,et al.  On‐line expectation–maximization algorithm for latent data models , 2009 .