Target language preposition selection – an experiment with transformation based learning and aligned bilingual data

The translation of prepositions is often considered one of the more difficult tasks within the field of machine translation. We describe an experiment using transformation- based learning to induce rules to select the appropriate target language preposition from aligned bilingual data. Results show an accuracy of 84.9%, to be compared with a baseline of 75.5%, where the most frequent translation alternative is always chosen.

[1]  Torbjörn Lager,et al.  Sense and Deduction: The Power of Peewees Applied to the SENSEVAL-2 Swedish Lexical Sample Task , 2001, *SEMEVAL.

[2]  Thorsten Brants,et al.  TnT – A Statistical Part-of-Speech Tagger , 2000, ANLP.

[3]  Robert L. Mercer,et al.  A Statistical Approach to Sense Disambiguation in Machine Translation , 1991, HLT.

[4]  Robert L. Mercer,et al.  Word-Sense Disambiguation Using Statistical Methods , 1991, ACL.

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

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

[7]  Jesse Tseng,et al.  The representation and selection of prepositions , 2000 .

[8]  Eric Brill,et al.  A Rule-Based Approach to Prepositional Phrase Attachment Disambiguation , 1994, COLING.

[9]  Beatrice Santorini,et al.  Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[10]  Alon Itai,et al.  Word Sense Disambiguation Using a Second Language Monolingual Corpus , 1994, CL.

[11]  Hiroshi Kanayama.  An iterative algorithm for translation acquisition of adpositions. , 2002, TMI.

[12]  Constantine D. Spyropoulos,et al.  Learning Rules for Large Vocabulary Word Sense Disambiguation , 1999, IJCAI.

[13]  Torbjörn Lager.  The µ-TBL System: Logic Programming Tools for Transformation-Based Learning , 1999, CoNLL.

[14]  Eric Brill,et al.  Automatic Rule Acquisition for Spelling Correction , 1997, ICML.

[15]  John A. Carroll,et al.  Applied morphological processing of English , 2001, Natural Language Engineering.