Some of Them Can be Guessed! Exploring the Effect of Linguistic Context in Predicting Quantifiers

Open Access
Authors
Publication date 2018
Host editors
  • I. Gurevych
  • Y. Miyao
Book title ACL 2018 : The 56th Annual Meeting of the Association for Computational Linguistics
Book subtitle proceedings of the conference : July 15-20, 2018, Melbourne, Australia
ISBN (electronic)
  • 9781948087346
Event The 56th Annual Meeting of the Association for Computational Linguistics - ACL 2018
Volume | Issue number 2
Pages (from-to) 114-119
Publisher Stroudsburg, PA: The Association for Computational Linguistics
Organisations
  • Interfacultary Research - Institute for Logic, Language and Computation (ILLC)
Abstract
We study the role of linguistic context in predicting quantifiers (‘few’, ‘all’). We collect crowdsourced data from human participants and test various models in a local (single-sentence) and a global context (multi-sentence) condition. Models significantly out-perform humans in the former setting and are only slightly better in the latter. While human performance improves with more linguistic context (especially on proportional quantifiers), model performance suffers. Models are very effective in exploiting lexical and morpho-syntactic patterns; humans are better at genuinely understanding the meaning of the (global) context.
Document type Conference contribution
Language English
Published at https://doi.org/10.18653/v1/P18-2019
Published at https://arxiv.org/abs/1806.00354
Downloads
P18-2019 (Final published version)
Supplementary materials
Permalink to this page
Back