Cross-lingual and cross-domain discourse segmentation of entire documents
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Standard
Cross-lingual and cross-domain discourse segmentation of entire documents. / Braud, Chloé; Lacroix, Ophélie; Søgaard, Anders.
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics: Short papers. Bind 2 Association for Computational Linguistics, 2017. s. 237-243.Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Cross-lingual and cross-domain discourse segmentation of entire documents
AU - Braud, Chloé
AU - Lacroix, Ophélie
AU - Søgaard, Anders
PY - 2017/1/1
Y1 - 2017/1/1
N2 - Discourse segmentation is a crucial step in building end-to-end discourse parsers. However, discourse segmenters only exist for a few languages and domains. Typically they only detect intra-sentential segment boundaries, assuming gold standard sentence and token segmentation, and relying on high-quality syntactic parses and rich heuristics that are not generally available across languages and domains. In this paper, we propose statistical discourse segmenters for five languages and three domains that do not rely on gold pre-annotations. We also consider the problem of learning discourse segmenters when no labeled data is available for a language. Our fully supervised system obtains 89.5% F1 for English newswire, with slight drops in performance on other domains, and we report supervised and unsupervised (cross-lingual) results for five languages in total.
AB - Discourse segmentation is a crucial step in building end-to-end discourse parsers. However, discourse segmenters only exist for a few languages and domains. Typically they only detect intra-sentential segment boundaries, assuming gold standard sentence and token segmentation, and relying on high-quality syntactic parses and rich heuristics that are not generally available across languages and domains. In this paper, we propose statistical discourse segmenters for five languages and three domains that do not rely on gold pre-annotations. We also consider the problem of learning discourse segmenters when no labeled data is available for a language. Our fully supervised system obtains 89.5% F1 for English newswire, with slight drops in performance on other domains, and we report supervised and unsupervised (cross-lingual) results for five languages in total.
UR - http://www.scopus.com/inward/record.url?scp=85040622591&partnerID=8YFLogxK
U2 - 10.18653/v1/P17-2037
DO - 10.18653/v1/P17-2037
M3 - Article in proceedings
AN - SCOPUS:85040622591
VL - 2
SP - 237
EP - 243
BT - Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics
PB - Association for Computational Linguistics
T2 - 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
Y2 - 30 July 2017 through 4 August 2017
ER -
ID: 195013952