UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Extrapolation in NLP

Mitchell, J; Saito Stenetorp, PLEPS; Minervini, P; Riedel, S; (2018) Extrapolation in NLP. In: Proceedings of the Workshop on Generalization in the Age of Deep Learning. (pp. pp. 28-33). Association for Computational Linguistics (ACL): New Orleans, LA, USA. Green open access

[thumbnail of W18-1005.pdf]
Preview
Text
W18-1005.pdf - Accepted Version

Download (185kB) | Preview

Abstract

We argue that extrapolation to unseen data will often be easier for models that capture global structures, rather than just maximise their local fit to the training data. We show that this is true for two popular models: the Decomposable Attention Model and word2vec.

Type: Proceedings paper
Title: Extrapolation in NLP
Event: Proceedings of the Workshop on Generalization in the Age of Deep Learning
Open access status: An open access version is available from UCL Discovery
DOI: 10.18653/v1/W18-1005
Publisher version: https://www.aclweb.org/anthology/W18-1005/
Language: English
Additional information: This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10051393
Downloads since deposit
76Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item