Transliteration of name entity via improved statistical translation on character sequences

Yan Song, Chunyu Kit, Xiao Chen

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

17 Citations (Scopus)

Abstract

Transliteration of given parallel name entities can be formulated as a phrase-based statistical machine translation (SMT) process, via its routine procedure comprising training, optimization and decoding. In this paper, we present our approach to transliterating name entities using the log-linear phrase-based SMT on character sequences. Our proposed work improves the translation by using bidirectional models, plus some heuristic guidance integrated in the decoding process. Our evaluated results indicate that this approach performs well in all standard runs in the NEWS2009 Machine Transliteration Shared Task. © 2009 ACL and AFNLP.
Original languageEnglish
Title of host publicationNEWS 2009 - 2009 Named Entities Workshop: Shared Task on Transliteration - Proceedings of the Workshop, ACL-IJCNLP 2009
Place of PublicationStroudsburg, PA
PublisherAssociation for Computational Linguistics
Pages57-60
ISBN (Print)978-1-932432-57-2, 1-932432-57-4
Publication statusPublished - 7 Aug 2009
Event2009 Named Entities Workshop (NEWS 2009): Shared Task on Transliteration - Suntec, Singapore
Duration: 7 Aug 2009 → …
https://aclanthology.org/W09-35

Publication series

NameNEWS - Named Entities Workshop: Shared Task on Transliteration at the Joint Conference of the Annual Meeting of the ACL and the International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP

Conference

Conference2009 Named Entities Workshop (NEWS 2009)
PlaceSingapore
CitySuntec
Period7/08/09 → …
Internet address

Fingerprint

Dive into the research topics of 'Transliteration of name entity via improved statistical translation on character sequences'. Together they form a unique fingerprint.

Cite this