Translating implicit discourse connectives based on crosslingual annotation and alignment

Hongzheng Li, Philippe Langlais, Yaohong Jin

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

1 Citation (Scopus)

Abstract

Implicit discourse connectives and relations are distributed more widely in Chinese texts, when translating into English, such connectives are usually translated explicitly. Towards Chinese-English MT, in this paper we describe cross-lingual annotation and alignment of discourse connectives in a parallel corpus, describing related surveys and findings. We then conduct some evaluation experiments to testify the translation of implicit connectives and whether representing implicit connectives explicitly in source language can improve the final translation performance significantly. Preliminary results show it has little improvement by just inserting explicit connectives for implicit relations.

Original languageEnglish
Title of host publicationDiscoMT 2017 - Discourse in Machine Translation, Proceedings of the Workshop
PublisherAssociation for Computational Linguistics (ACL)
Pages93-98
Number of pages6
ISBN (Electronic)9781945626876
Publication statusPublished - 2017
Externally publishedYes
Event3rd Workshop on Discourse in Machine Translation, DiscoMT 2017, held in conjunction with EMNLP 2017 - Copenhagen, Denmark
Duration: 8 Sept 2017 → …

Publication series

NameDiscoMT 2017 - Discourse in Machine Translation, Proceedings of the Workshop

Conference

Conference3rd Workshop on Discourse in Machine Translation, DiscoMT 2017, held in conjunction with EMNLP 2017
Country/TerritoryDenmark
CityCopenhagen
Period8/09/17 → …

Fingerprint

Dive into the research topics of 'Translating implicit discourse connectives based on crosslingual annotation and alignment'. Together they form a unique fingerprint.

Cite this