Normal view MARC view ISBD view

Bilingual lexicon extraction from comparable corpora for closely related languages / Fišer, Darja ; Ljubešić, Nikola.

By: Fišer, Darja.
Contributor(s): Ljubešić, Nikola, informatičar [aut].
Material type: ArticleArticleDescription: 125-131 str.Other title: Bilingual Lexicon Extraction from Comparable Corpora for Closely Related Languages [Naslov na engleskom:].Subject(s): 5.04 | comparable corpora, lexicon extraction, closely related languages hrv | comparable corpora, lexicon extraction, closely related languages engOnline resources: Elektronička verzija In: Recent Advances in Natural Language Processing 2011 (12-14.09.2011. ; Hissar, Bugarska) Proceedings of the International Conference Recent Advances in Natural Language Processing 2011 str. 125-131Summary: In this paper we present a knowledge-light approach to extract a bilingual lexicon for closely related languages from comparable corpora. While in most related work an existing dictionary is used to translate context vectors, we take advantage of the similarities between languages instead and build a seed lexicon from words that are identical in both languages and then further extend it with context-based cognates and translations of the most frequent words. We also use cognates for reranking translation candidates obtained via context similarity and extract translation equivalents for all content words, not just nouns as in most related work. The results are very encouraging, suggesting that other similar languages could bene- fit from the same approach. By enlarging the seed lexicon with cognates and translations of the most frequent words and by cognate-based reranking of translation candidates we were able to improve the average baseline precision from 0.592 to 0.797 on the mean reciprocal rank for the ten top- ranking translation candidates for nouns, verbs and adjectives with a 46% recall on the gold standard of 1000 random entries from a traditional dictionary.
Tags from this library: No tags from this library for this title. Log in to add tags.
No physical items for this record

In this paper we present a knowledge-light approach to extract a bilingual lexicon for closely related languages from comparable corpora. While in most related work an existing dictionary is used to translate context vectors, we take advantage of the similarities between languages instead and build a seed lexicon from words that are identical in both languages and then further extend it with context-based cognates and translations of the most frequent words. We also use cognates for reranking translation candidates obtained via context similarity and extract translation equivalents for all content words, not just nouns as in most related work. The results are very encouraging, suggesting that other similar languages could bene- fit from the same approach. By enlarging the seed lexicon with cognates and translations of the most frequent words and by cognate-based reranking of translation candidates we were able to improve the average baseline precision from 0.592 to 0.797 on the mean reciprocal rank for the ten top- ranking translation candidates for nouns, verbs and adjectives with a 46% recall on the gold standard of 1000 random entries from a traditional dictionary.

Projekt MZOS 130-1301679-1380

ENG

There are no comments for this item.

Log in to your account to post a comment.

Powered by Koha

//