Automatic Phrase Alignment: Using Statistical N-Gram Alignment for Syntactic Phrase Alignment
2007 (English)In: Proceedings of the Sixth International Workshop on Treebanks and Linguistic Theories (TLT 2007) / [ed] Koenraad De Smedt, Jan Hajič and Sandra Kübler, Northern European Association for Language Technology (NEALT) , 2007, 139-150 p.Conference paper (Refereed)
A parallel treebank consists of syntactically annotated sentences in two or more languages, taken from translated documents. These parallel sentences are linked through alignment. This paper explores the use of word n-gram alignment, computed for statistical machine translation, to create syntactic phrase alignment. We achieve a weighted F0.5-score of over 65%.
Place, publisher, year, edition, pages
Northern European Association for Language Technology (NEALT) , 2007. 139-150 p.
, NEALT Proceedings Series
parallel treebank, alignment
Language Technology (Computational Linguistics)
IdentifiersURN: urn:nbn:se:su:diva-10561OAI: oai:DiVA.org:su-10561DiVA: diva2:177080
Sixth International Workshop on Treebanks and Linguistic Theories (TLT 2007)