Learning Translation Templates from Bilingual Translation Examples

A mechanism for learning lexical correspondences between two languages from sets of translated sentence pairs is presented. These lexical level correspondences are learned using analogical reasoning between two translation examples. Given two translation examples, the similar parts of the sentences in the source language must correspond to the similar parts of the sentences in the target language. Similarly, the different parts must correspond to the respective parts in the translated sentences. The correspondences between similarities and between differences are learned in the form of translation templates. A translation template is a generalized translation exemplar pair where some components are generalized by replacing them with variables in both sentences and establishing bindings between these variables. The learned translation templates are obtained by replacing differences or similarities by variables. This approach has been implemented and tested on a set of sample training datasets and produced promising results for further investigation.

[1]  MBT2: A Method for Combining Fragments of Examples in Example-Based Translation , 1995, Artif. Intell..

[2]  Ralf D. Brown.  Automated Dictionary Extraction for “Knowledge-Free” Example-Based Translation , 2006 .

[3]  Dekai Wu,et al.  Large-scale automatic extraction of an English-Chinese translation lexicon , 2004, Machine Translation.

[4]  Makoto Nagao,et al.  A framework of a mechanical translation between Japanese and English by analogy principle , 1984 .

[5]  Hitoshi Iida,et al.  Experiments and Prospects of Example-Based Machine Translation , 1991, ACL.

[6]  Teruko Mitamura,et al.  The KANT System: Fast, Accurate, High-Quality Translation in Practical Domains , 1992, COLING.

[7]  Douglas L. Medin,et al.  Context theory of classification learning. , 1978 .

[8]  Sergei Nirenburg,et al.  A Full-Text Experiment in Example-Based Machine Translation , 1994 .

[9]  Janet L. Kolodner,et al.  Case-Based Learning , 1993, Springer US.

[10]  Ilyas Cicekli,et al.  Ordering Translation Templates by Assigning Confidence Factors , 1998, AMTA.

[11]  Ivan A. Sag,et al.  Information-based syntax and semantics , 1987 .

[12]  Satoshi Sato,et al.  Toward Memory-based Translation , 1990, COLING.

[13]  Ralf D. Brown,et al.  Example-Based Machine Translation in the Pangloss System , 1996, COLING.

[14]  Ashwin Ram,et al.  Indexing, Elaboration and Refinement: Incremental Learning of Explanatory Cases , 1993, Machine Learning.

[15]  H. Altay Güvenir,et al.  Learning Translation Templates from Examples , 1998, Inf. Syst..

[16]  H. Altay Güvenir,et al.  Learning Translation Rules From A Bilingual Corpus , 1996, ArXiv.

[17]  Hitoshi Iida,et al.  Cooperation between Transfer and Analysis in Example-Based Framework , 1992, COLING.

[18]  Teruko Mitamura,et al.  Acquisition of large lexicons for practical knowledge-based MT , 2004, Machine Translation.

[19]  Geoffrey K. Pullum,et al.  Generalized Phrase Structure Grammar , 1985 .

[20]  Hiroyuki Kaji,et al.  Learning Translation Templates From Bilingual Text , 1992, COLING.

[21]  Hiroaki Kitano,et al.  A Comprehensive and Practical Model of Memory-Based Machine Translation , 1993, IJCAI.

[22]  H. Altay Güvenir,et al.  Corpus-Based Learning of Generalized parse Tree Rules for Translation , 1996, Canadian Conference on AI.

[23]  Vasileios Hatzivassiloglou,et al.  Translating Collocations for Bilingual Lexicons: A Statistical Approach , 1996, CL.