Cross-lingual discourse relation analysis: a corpus study and a semi-supervised classification system

From National Research Council Canada

AuthorSearch for: ; Search for: 1; Search for:
Name affiliation
  1. National Research Council Canada. Information and Communication Technologies
FormatText
TypeArticle
Proceedings title25th International Conference on Computational Linguistics
Conference25th International Conference on Computational Linguistics, August 23-29 2014, Dublin, Ireland
ISBN978-1-63439-195-5
Volume1
Pages577–586
Abstract
We present a cross-lingual discourse relation analysis based on a parallel corpus with discourse information available only for one language. First, we conduct a corpus study to explore differences in discourse organization between Chinese and English, including differences in information packaging, implicit/explicit discourse expression divergence, and discourse connective ambiguities. Second, we introduce a novel approach to learning to recognize discourse relations, using the parallel corpus instead of discourse annotation in the language of interest. Our resulting semi-supervised system reaches state-of-art performance on the task of discourse relation detection, and outperforms a supervised system on discourse relation classification.
Publication date
PublisherAssociation for Computational Linguistics
LanguageEnglish
Peer reviewedYes
NPARC number23000181
Export citationExport as RIS
Report a correctionReport a correction
Record identifier0d21da88-d16f-46e9-8f54-faea7be00c89
Record created2016-06-16
Record modified2016-06-16
Report a problem on this page
Date modified: