Estimating linear models for compositional distributional semantics

Fabio Massimo Zanzotto, Ioannis Korkontzelos, Francesca Fallucchi, Suresh Manandhar

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

    Abstract

    In distributional semantics studies, there is a growing attention in compositionally determining the distributional meaning of word sequences. Yet, compositional distributional models depend on a large set of parameters that have not been explored. In this paper we propose a novel approach to estimate parameters for a class of compositional distributional models: the additive models. Our approach leverages on two main ideas. Firstly, a novel idea for extracting compositional distributional semantics examples. Secondly, an estimation method based on regression models for multiple dependent variables. Experiments demonstrate that our approach outperforms existing methods for determining a good model for compositional distributional semantics.
    Original languageEnglish
    Title of host publicationColing 2010 - 23rd International Conference on Computational Linguistics, Proceedings of the Conference|Coling - Int. Conf. Comput. Linguist., Proc. Conf.
    PublisherAssociation for Computational Linguistics
    Pages1263-1271
    Number of pages8
    Volume2
    Publication statusPublished - 2010
    Event23rd International Conference on Computational Linguistics, Coling 2010 - Beijing
    Duration: 1 Jul 2010 → …

    Publication series

    NameCOLING '10

    Conference

    Conference23rd International Conference on Computational Linguistics, Coling 2010
    CityBeijing
    Period1/07/10 → …

    Fingerprint

    Dive into the research topics of 'Estimating linear models for compositional distributional semantics'. Together they form a unique fingerprint.

    Cite this