Improved Statistical Machine Translation by Cross-Linguistic Projection of Named Entities Recognition and Translation

Fuente: Redalyc
Salvato in:
Dettagli Bibliografici
Autore principale: Rahma Sellami
Natura: Artículo científico
Lingua:en
Pubblicazione: Instituto Politécnico Nacional 2015
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1876467130130497536
author Rahma Sellami
author_facet Rahma Sellami
contents Improved Statistical Machine Translation by Cross-Linguistic Projection of Named Entities Recognition and Translation Rahma Sellami Fatima Deffaf Fatiha Sadat Lamia Hadrich Belguith Computación Named entity pivot language machine translation One of the existing difficulties in natural lan- guage processing applications is the lack of appropri- ate tools for the recognition, translation, and/or translit- eration of named entities (NEs), specifically for less- resourced languages. In this paper, we propose a new method to automatically label multilingual parallel data for Arabic-French pair of languages with named entity tags and build lexicons of those named entities with their transliteration and/or translation in the target language. For this purpose, we bring in a third well-resourced language, English, that might serve as pivot, in order to build an Arabic-French NE Translation lexicon. Eval- uations on the Arabic-French pair of languages using English as pivot in the transitive model showed the ef- fectiveness of the proposed method for mining Arabic- French named entities and their translations. Moreover, the integration of this component in statistical machine translation outperformed the baseline system. 2015 artículo científico 1405-5546 https://www.redalyc.org/articulo.oa?id=61543181007 en http://www.redalyc.org/revista.oa?id=615 Computación y Sistemas application/pdf Instituto Politécnico Nacional Computación y Sistemas (México) Num.4 Vol.19
format Artículo científico
id redalyc_61543181007
institution Redalyc
language en
publishDate 2015
publisher Instituto Politécnico Nacional
spellingShingle Improved Statistical Machine Translation by Cross-Linguistic Projection of Named Entities Recognition and Translation
Rahma Sellami
Computación
Named entity
pivot language
machine translation
Improved Statistical Machine Translation by Cross-Linguistic Projection of Named Entities Recognition and Translation Rahma Sellami Fatima Deffaf Fatiha Sadat Lamia Hadrich Belguith Computación Named entity pivot language machine translation One of the existing difficulties in natural lan- guage processing applications is the lack of appropri- ate tools for the recognition, translation, and/or translit- eration of named entities (NEs), specifically for less- resourced languages. In this paper, we propose a new method to automatically label multilingual parallel data for Arabic-French pair of languages with named entity tags and build lexicons of those named entities with their transliteration and/or translation in the target language. For this purpose, we bring in a third well-resourced language, English, that might serve as pivot, in order to build an Arabic-French NE Translation lexicon. Eval- uations on the Arabic-French pair of languages using English as pivot in the transitive model showed the ef- fectiveness of the proposed method for mining Arabic- French named entities and their translations. Moreover, the integration of this component in statistical machine translation outperformed the baseline system. 2015 artículo científico 1405-5546 https://www.redalyc.org/articulo.oa?id=61543181007 en http://www.redalyc.org/revista.oa?id=615 Computación y Sistemas application/pdf Instituto Politécnico Nacional Computación y Sistemas (México) Num.4 Vol.19
title Improved Statistical Machine Translation by Cross-Linguistic Projection of Named Entities Recognition and Translation
topic Computación
Named entity
pivot language
machine translation
url https://www.redalyc.org/articulo.oa?id=61543181007