Does syntax help discourse segmentation? Not so much

Chloé Braud, Ophélie Lacroix, Anders Søgaard


Abstract
Discourse segmentation is the first step in building discourse parsers. Most work on discourse segmentation does not scale to real-world discourse parsing across languages, for two reasons: (i) models rely on constituent trees, and (ii) experiments have relied on gold standard identification of sentence and token boundaries. We therefore investigate to what extent constituents can be replaced with universal dependencies, or left out completely, as well as how state-of-the-art segmenters fare in the absence of sentence boundaries. Our results show that dependency information is less useful than expected, but we provide a fully scalable, robust model that only relies on part-of-speech information, and show that it performs well across languages in the absence of any gold-standard annotation.
Anthology ID:
D17-1258
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2432–2442
Language:
URL:
https://www.aclweb.org/anthology/D17-1258
DOI:
10.18653/v1/D17-1258
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D17-1258.pdf
Video:
 https://vimeo.com/238232586