Can Discourse Relations be Identified Incrementally?

Frances Yung, Hiroshi Noji, Yuji Matsumoto


Abstract
Humans process language word by word and construct partial linguistic structures on the fly before the end of the sentence is perceived. Inspired by this cognitive ability, incremental algorithms for natural language processing tasks have been proposed and demonstrated promising performance. For discourse relation (DR) parsing, however, it is not yet clear to what extent humans can recognize DRs incrementally, because the latent ‘nodes’ of discourse structure can span clauses and sentences. To answer this question, this work investigates incrementality in discourse processing based on a corpus annotated with DR signals. We find that DRs are dominantly signaled at the boundary between the two constituent discourse units. The findings complement existing psycholinguistic theories on expectation in discourse processing and provide direction for incremental discourse parsing.
Anthology ID:
I17-2027
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Greg Kondrak, Taro Watanabe
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
157–162
Language:
URL:
https://aclanthology.org/I17-2027
DOI:
Bibkey:
Cite (ACL):
Frances Yung, Hiroshi Noji, and Yuji Matsumoto. 2017. Can Discourse Relations be Identified Incrementally?. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 157–162, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Can Discourse Relations be Identified Incrementally? (Yung et al., IJCNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/I17-2027.pdf
Note:
 I17-2027.Notes.pdf
Dataset:
 I17-2027.Datasets.tgz