Simple negation scope resolution through deep parsing: A semantic solution to a semantic problem

Woodley Packard, Emily Bender, Jonathon Read, Stephan Oepen, Rebecca Dridan

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    105 Downloads (Pure)

    Abstract

    In this work, we revisit Shared Task 1 from the 2012 *SEM Conference: the automated analysis of negation. Unlike the vast majority of participating systems in 2012, our approach works over explicit and formal representations of propositional semantics, i.e. derives the notion of negation scope assumed in this task from the structure of logical-form meaning representations. We relate the task-specific interpretation of (negation) scope to the concept of (quantifier and operator) scope in mainstream underspecified semantics. With reference to an explicit encoding of semantic predicate-argument structure, we can operationalize the annotation decisions made for the 2012 *SEM task, and demonstrate how a comparatively simple system for negation scope resolution can be built from an off-the-shelf deep parsing system. In a system combination setting, our approach improves over the best published results on this task to date.
    Original languageEnglish
    Title of host publicationConference: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
    PublisherAssociation for Computational Linguistics (ACL)
    Publication statusPublished - 2014
    Event52nd Annual Meeting of the Association for Computational Linguistics - Balitmore, United States
    Duration: 22 Jun 201427 Jun 2014

    Conference

    Conference52nd Annual Meeting of the Association for Computational Linguistics
    Country/TerritoryUnited States
    CityBalitmore
    Period22/06/1427/06/14

    Fingerprint

    Dive into the research topics of 'Simple negation scope resolution through deep parsing: A semantic solution to a semantic problem'. Together they form a unique fingerprint.

    Cite this