Mining Discourse Markers for Unsupervised Sentence Representation Learning

Damien Sileo, Tim Van De Cruys, Camille Pradel, Philippe Muller


Abstract
Current state of the art systems in NLP heavily rely on manually annotated datasets, which are expensive to construct. Very little work adequately exploits unannotated data – such as discourse markers between sentences – mainly because of data sparseness and ineffective extraction methods. In the present work, we propose a method to automatically discover sentence pairs with relevant discourse markers, and apply it to massive amounts of data. Our resulting dataset contains 174 discourse markers with at least 10k examples each, even for rare markers such as “coincidentally” or “amazingly”. We use the resulting data as supervision for learning transferable sentence embeddings. In addition, we show that even though sentence representation learning through prediction of discourse marker yields state of the art results across different transfer tasks, it’s not clear that our models made use of the semantic relation between sentences, thus leaving room for further improvements.
Anthology ID:
N19-1351
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3477–3486
Language:
URL:
https://aclanthology.org/N19-1351
DOI:
10.18653/v1/N19-1351
Bibkey:
Cite (ACL):
Damien Sileo, Tim Van De Cruys, Camille Pradel, and Philippe Muller. 2019. Mining Discourse Markers for Unsupervised Sentence Representation Learning. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3477–3486, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Mining Discourse Markers for Unsupervised Sentence Representation Learning (Sileo et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1351.pdf
Video:
 https://aclanthology.org/N19-1351.mp4
Code
 synapse-developpement/Discovery
Data
Discovery