NCU IISR English-Korean and English-Chinese Named Entity Transliteration Using Different Grapheme Segmentation Approaches

Yu Chun Wang, Chun Kai Wu, Richard Tzong Han Tsai

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper describes our approach to English-Korean and English-Chinese transliteration task of NEWS 2015. We use different grapheme segmentation approaches on source and target languages to train several transliteration models based on the M2M-aligner and DirecTL+, a string transduction model. Then, we use two reranking techniques based on string similarity and web co-occurrence to select the best transliteration among the prediction results from the different models. Our English-Korean standard and non-standard runs achieve 0.4482 and 0.5067 in top-1 accuracy respectively, and our English-Chinese standard runs achieves 0.2925 in top-1 accuracy. c 2015 Association for Computational Linguistics.

Original languageEnglish
Title of host publicationProceedings of the 15th Named Entity Workshop, NEWS 2015 - Held as part ACL 2015
EditorsXiangyu Duan, Rafael E. Banchs, Min Zhang, Haizhou Li, A. Kumara
PublisherAssociation for Computational Linguistics (ACL)
Pages83-87
Number of pages5
ISBN (Electronic)9781941643655
StatePublished - 2015
Event15th Named Entity Workshop, NEWS 2015 - Beijing, China
Duration: 31 Jul 2015 → …

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
Volume2015-July
ISSN (Print)0736-587X

Conference

Conference15th Named Entity Workshop, NEWS 2015
Country/TerritoryChina
CityBeijing
Period31/07/15 → …

Fingerprint

Dive into the research topics of 'NCU IISR English-Korean and English-Chinese Named Entity Transliteration Using Different Grapheme Segmentation Approaches'. Together they form a unique fingerprint.

Cite this