Publication

The Other Side of the Coin: Unsupervised Disambiguation of Potentially Idiomatic Expressions by Contrasting Senses

Haagsma, H., Nissim, M. & Bos, J., Aug-2018, Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018) . Association for Computational Linguistics (ACL), p. 178-184 7 p.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Disambiguation of potentially idiomatic expressions involves determining the sense of a potentially idiomatic expression in a given context, e.g. determining that make hay in ‘Investment banks made hay while takeovers shone.’ is used in a figurative sense. This enables automatic interpretation of idiomatic expressions, which is important for applications like machine translation and sentiment analysis. In this work, we present an unsupervised approach for English that makes use of literalisations of idiom senses to improve disambiguation, which is based on the lexical cohesion graph-based method by Sporleder and Li (2009). Experimental results show that, while literalisation carries novel information, its performance falls short of that of state-of-the-art
unsupervised methods.
Original languageEnglish
Title of host publicationProceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018)
PublisherAssociation for Computational Linguistics (ACL)
Pages178-184
Number of pages7
Publication statusPublished - Aug-2018
Related Activities
  1. Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018)

    Hessel Haagsma (Speaker)
    25-Aug-201826-Aug-2018

    Activity: Talk or presentationAcademic

  2. The 27th International Conference on Computational Linguistics (COLING 2018)

    Hessel Haagsma (Participant)
    20-Aug-201826-Aug-2018

    Activity: Participating in or organising an eventParticipation in conferenceAcademic

View all (2) »

Download statistics

No data available

ID: 74538914