A Pattern Matching method for finding Noun and Proper Noun Translations from Noisy Parallel Corpora

Simple item page
dc.creatorFung, Pascale
dc.date1995-05-06
dc.date.accessioned2026-07-07T09:09:49Z
dc.date.available2026-07-07T09:09:49Z
dc.descriptionWe present a pattern matching method for compiling a bilingual lexicon of nouns and proper nouns from unaligned, noisy parallel texts of Asian/Indo-European language pairs. Tagging information of one language is used. Word frequency and position information for high and low frequency words are represented in two different vector forms for pattern matching. New anchor point finding and noise elimination techniques are introduced. We obtained a 73.1\% precision. We also show how the results can be used in the compilation of domain-specific noun phrases.
dc.description8 pages, uuencoded compressed postscript file. To appear in the Proceedings of the 33rd ACL
dc.identifierhttps://arxiv.org/abs/cmp-lg/9505016
dc.identifierhttp://arxiv.org/abs/cmp-lg/9505016
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/151175
dc.subjectComputation and Language
dc.titleA Pattern Matching method for finding Noun and Proper Noun Translations from Noisy Parallel Corpora
dc.typetext

Files

Collections

arXiv