Using Word Vectors to Improve Word Alignments for Low Resource Machine Translation

We present a method for improving word alignments using word similarities. This method is based on encouraging common alignment links between semantically similar words. We use word vectors trained on monolingual data to estimate similarity. Our experiments on translating fifteen languages into English show consistent BLEU score improvements across the languages.

[1]  Jörg Tiedemann,et al.  Combining Clues for Word Alignment , 2003, EACL.

[2]  Young-Suk Lee,et al.  Morphological Analysis for Statistical Machine Translation , 2004, NAACL.

[3]  Murat Saraclar,et al.  Bayesian Word Alignment for Statistical Machine Translation , 2011, ACL.

[4]  Ashish Vaswani,et al.  Smaller Alignment Models for Better Translations: Unsupervised Word Alignment with the l0-norm , 2012, ACL.

[5]  Theerawat Songyot,et al.  Improving Word Alignment using Word Similarity , 2014, EMNLP.

[6]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

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

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

[9]  Kevin Knight,et al.  Using Syntax to Improve Word Alignment Precision for Syntax-Based Machine Translation , 2008, WMT@ACL.

[10]  Hui Zhang,et al.  Kneser-Ney Smoothing on Expected Counts , 2014, ACL.

[11]  Ulf Hermjakob,et al.  Improved Word Alignment with Statistics and Linguistic Heuristics , 2009, EMNLP.

[12]  Philipp Koehn,et al.  Six Challenges for Neural Machine Translation , 2017, NMT@ACL.

[13]  Phil Blunsom,et al.  Learning Bilingual Word Representations by Marginalizing Alignments , 2014, ACL.

[14]  Jeff Z. Ma,et al.  Improving Low-Resource Statistical Machine Translation with a Novel Semantic Word Clustering Algorithm , 2011, MTSUMMIT.

[15]  Yang Gao,et al.  Aligning English Strings with Abstract Meaning Representation Graphs , 2014, EMNLP.

[16]  Ben Taskar,et al.  Alignment by Agreement , 2006, NAACL.

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

[18]  Colin Cherry,et al.  Soft Syntactic Constraints for Word Alignment through Discriminative Training , 2006, ACL.

[19]  Vuong Van Bui,et al.  Smoothing parameter estimation framework for IBM word alignment models , 2016 .

[20]  Christopher D. Manning,et al.  Extentions to HMM-based Statistical Word Alignment Models , 2002, EMNLP.

[21]  Heshaam Faili,et al.  TEP: Tehran English-Persian Parallel Corpus , 2011, CICLing.

[22]  Thorsten Brants,et al.  One billion word benchmark for measuring progress in statistical language modeling , 2013, INTERSPEECH.

[23]  José B. Mariño,et al.  Improving Statistical Word Alignments with Morpho-syntactic Transformations , 2006, FinTAL.

[24]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[25]  Robert C. Moore.  Improving IBM Word Alignment Model 1 , 2004, ACL.