Entailment Semantics Can Be Extracted from an Ideal Language Model

William Merrill, Alex Warstadt, Tal Linzen

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

    Abstract

    Language models are often trained on text alone, without additional grounding. There is debate as to how much of natural language semantics can be inferred from such a procedure. We prove that entailment judgments between sentences can be extracted from an ideal language model that has perfectly learned its target distribution, assuming the training sentences are generated by Gricean agents, i.e., agents who follow fundamental principles of communication from the linguistic theory of pragmatics. We also show entailment judgments can be decoded from the predictions of a language model trained on such Gricean data. Our results reveal a pathway for understanding the semantic information encoded in unlabeled linguistic data and a potential framework for extracting semantics from language models.

    Original languageEnglish (US)
    Title of host publicationCoNLL 2022 - 26th Conference on Computational Natural Language Learning, Proceedings of the Conference
    PublisherAssociation for Computational Linguistics (ACL)
    Pages176-193
    Number of pages18
    ISBN (Electronic)9781959429074
    StatePublished - 2022
    Event26th Conference on Computational Natural Language Learning, CoNLL 2022 collocated and co-organized with EMNLP 2022 - Abu Dhabi, United Arab Emirates
    Duration: Dec 7 2022Dec 8 2022

    Publication series

    NameCoNLL 2022 - 26th Conference on Computational Natural Language Learning, Proceedings of the Conference

    Conference

    Conference26th Conference on Computational Natural Language Learning, CoNLL 2022 collocated and co-organized with EMNLP 2022
    Country/TerritoryUnited Arab Emirates
    CityAbu Dhabi
    Period12/7/2212/8/22

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Human-Computer Interaction
    • Linguistics and Language

    Fingerprint

    Dive into the research topics of 'Entailment Semantics Can Be Extracted from an Ideal Language Model'. Together they form a unique fingerprint.

    Cite this