Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Towards a seamless integration of word senses into downstream NLP applications

Pilehvar, Mohammad Taher, Camacho Collados, Jose ORCID: https://orcid.org/0000-0003-1618-7239, Navigli, Roberto and Collier, Nigel 2017. Towards a seamless integration of word senses into downstream NLP applications. Presented at: The 55th Annual Meeting of the Association for Computational Linguistics, Vancouver, Canada, 30th July - 4th August 2017. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA: The Association for Computational Linguistics, pp. 1857-1869. 10.18653/v1/P17-1170

Full text not available from this repository.

Abstract

Lexical ambiguity can impede NLP systems from accurate understanding of semantics. Despite its potential benefits, the integration of sense-level information into NLP systems has remained understudied. By incorporating a novel disambiguation algorithm into a state-of-the-art classification model, we create a pipeline to integrate sense-level information into downstream NLP applications. We show that a simple disambiguation of the input text can lead to consistent performance improvement on multiple topic categorization and polarity detection datasets, particularly when the fine granularity of the underlying sense inventory is reduced and the document is sufficiently large. Our results also point to the need for sense representation research to focus more on in vivo evaluations which target the performance in downstream NLP applications rather than artificial benchmarks.

Item Type: Conference or Workshop Item (Paper)
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Publisher: The Association for Computational Linguistics
ISBN: 978-1-945626-75-3
Last Modified: 24 Oct 2022 07:04
URI: https://orca.cardiff.ac.uk/id/eprint/114045

Citation Data

Cited 31 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item