Conneau, A., Kiela, D., Schwenk, H. et al. (2 more authors) (2017) Supervised learning of universal sentence representations from natural language inference data. In: Palmer, M., Hwa, R. and Riedel, S., (eds.) Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing, 07-11 Sep 2017, Copenhagen, Denmark. Association for Computational Linguistics , pp. 670-680. ISBN 9781945626838
Abstract
Many modern NLP systems rely on word embeddings, previously trained in an unsupervised manner on large corpora, as base features. Efforts to obtain embeddings for larger chunks of text, such as sentences, have however not been so successful. Several attempts at learning unsupervised representations of sentences have not reached satisfactory enough performance to be widely adopted. In this paper, we show how universal sentence representations trained using the supervised data of the Stanford Natural Language Inference datasets can consistently outperform unsupervised methods like SkipThought vectors on a wide range of transfer tasks. Much like how computer vision uses ImageNet to obtain features, which can then be transferred to other tasks, our work tends to indicate the suitability of natural language inference for transfer learning to other NLP tasks. Our encoder is publicly available.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Editors: |
|
Copyright, Publisher and Additional Information: | © 2017 Association for Computational Linguistics. This is an author-produced version of a paper subsequently published in the ACL Anthology. Uploaded in accordance with the publisher's self-archiving policy. |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 11 Dec 2019 15:48 |
Last Modified: | 13 Dec 2019 02:41 |
Published Version: | https://www.aclweb.org/anthology/D17-1070.pdf |
Status: | Published |
Publisher: | Association for Computational Linguistics |
Refereed: | Yes |
Identification Number: | 10.18653/v1/D17-1070 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:154417 |