Discriminative Word Alignment via Alignment Matrix Modeling

In this paper a new discriminative word alignment method is presented. This approach models directly the alignment matrix by a conditional random field (CRF) and so no restrictions to the alignments have to be made. Furthermore, it is easy to add features and so all available information can be used. Since the structure of the CRFs can get complex, the inference can only be done approximately and the standard algorithms had to be adapted. In addition, different methods to train the model have been developed. Using this approach the alignment quality could be improved by up to 23 percent for 3 different language pairs compared to a combination of both IBM4-alignments. Furthermore the word alignment was used to generate new phrase tables. These could improve the translation quality significantly.

[1]  Ted Pedersen,et al.  An Evaluation Exercise for Word Alignment , 2003, ParallelTexts@NAACL-HLT.

[2]  Ben Taskar,et al.  Word Alignment via Quadratic Assignment , 2006, NAACL.

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

[4]  Andreas Bode,et al.  Improved Discriminative Bilingual Word Alignment , 2006, ACL.

[5]  Michael J. Black,et al.  Efficient Belief Propagation with Learned Higher-Order Markov Random Fields , 2006, ECCV.

[6]  Chin-Hui Lee,et al.  A maximal figure-of-merit (MFoM)-learning approach to robust classifier design for text categorization , 2006, ACM Trans. Inf. Syst..

[7]  Fernando Pereira,et al.  Shallow Parsing with Conditional Random Fields , 2003, NAACL.

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

[9]  Lluís Padró,et al.  FreeLing 1.3: Syntactic and semantic services in an open-source NLP library , 2006, LREC.

[10]  Phil Blunsom,et al.  Discriminative Word Alignment with Conditional Random Fields , 2006, ACL.

[11]  Alexander M. Fraser,et al.  Squibs and Discussions: Measuring Word Alignment Quality for Statistical Machine Translation , 2007, CL.

[12]  Dan Klein,et al.  Fast Exact Inference with a Factored Model for Natural Language Parsing , 2002, NIPS.

[13]  Daniel Marcu,et al.  Statistical Phrase-Based Translation , 2003, NAACL.

[14]  William T. Freeman,et al.  Understanding belief propagation and its generalizations , 2003 .

[15]  Ying Zhang.  Measuring Confidence Intervals for MT Evaluation Metrics , 2004 .

[16]  Eric Brill,et al.  Transformation-Based Error-Driven Learning and Natural Language Processing: A Case Study in Part-of-Speech Tagging , 1995, CL.

[17]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

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

[19]  Jun Suzuki,et al.  Training Conditional Random Fields with Multivariate Evaluation Measures , 2006, ACL.

[20]  Helmut Schmidt,et al.  Probabilistic part-of-speech tagging using decision trees , 1994 .

[21]  Daniel Jurafsky,et al.  A Conditional Random Field Word Segmenter for Sighan Bakeoff 2005 , 2005, IJCNLP.

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

[23]  S. Vogel,et al.  SMT decoder dissected: word reordering , 2003, International Conference on Natural Language Processing and Knowledge Engineering, 2003. Proceedings. 2003.

[24]  Gerhard Lakemeyer,et al.  Exploring artificial intelligence in the new millennium , 2003 .

[25]  José B. Mariño,et al.  Guidelines for Word Alignment Evaluation and Manual Alignment , 2005, Lang. Resour. Evaluation.