Detecting compositionality in multi-word expressions

Ioannis Korkontzelos, Suresh Manandhar

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

    Abstract

    Identifying whether a multi-word expression (MWE) is compositional or not is important for numerous NLP applications. Sense induction can partition the context of MWEs into semantic uses and therefore aid in deciding compositionality. We propose an unsupervised system to explore this hypothesis on compound nominals, proper names and adjective-noun constructions, and evaluate the contribution of sense induction. The evaluation set is derived from WordNet in a semi-supervised way. Graph connectivity measures are employed for unsupervised parameter tuning. © 2009 ACL and AFNLP.
    Original languageEnglish
    Title of host publicationACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.|ACL-IJCNLP - Jt. Conf. Annu. Meet. Assoc. Comput. Linguist. Int. Jt. Conf. Nat. Lang. Process. AFNLP, Proc. Conf.
    Pages65-68
    Number of pages3
    Publication statusPublished - 2009
    EventJoint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009 - Suntec
    Duration: 1 Jul 2009 → …
    http://www-users.cs.york.ac.uk/\ {}suresh/papers/DCMW.pdf

    Conference

    ConferenceJoint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009
    CitySuntec
    Period1/07/09 → …
    Internet address

    Keywords

    • file-import-09-11-19

    Fingerprint

    Dive into the research topics of 'Detecting compositionality in multi-word expressions'. Together they form a unique fingerprint.

    Cite this