The Language Model Understood the Prompt was Ambiguous: Probing Syntactic Uncertainty Through Generation

Laura Aina, Tal Linzen

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

    Abstract

    Temporary syntactic ambiguities arise when the beginning of a sentence is compatible with multiple syntactic analyses. We inspect to which extent neural language models (LMs) exhibit uncertainty over such analyses when processing temporarily ambiguous inputs, and how that uncertainty is modulated by disambiguating cues. We probe the LM’s expectations by generating from it: we use stochastic decoding to derive a set of sentence completions, and estimate the probability that the LM assigns to each interpretation based on the distribution of parses across completions. Unlike scoring-based methods for targeted syntactic evaluation, this technique makes it possible to explore completions that are not hypothesized in advance by the researcher. We apply this method to study the behavior of two LMs (GPT2 and an LSTM) on three types of temporary ambiguity, using materials from human sentence processing experiments. We find that LMs can track multiple analyses simultaneously; the degree of uncertainty varies across constructions and contexts. As a response to disambiguating cues, the LMs often select the correct interpretation, but occasional errors point to potential areas of improvement.

    Original languageEnglish (US)
    Title of host publicationBlackboxNLP 2021 - Proceedings of the 4th BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
    PublisherAssociation for Computational Linguistics (ACL)
    Pages42-57
    Number of pages16
    ISBN (Electronic)9781955917063
    StatePublished - 2021
    Event4th BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, BlackboxNLP 2021 - Virtual, Punta Cana, Dominican Republic
    Duration: Nov 11 2021 → …

    Publication series

    NameBlackboxNLP 2021 - Proceedings of the 4th BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP

    Conference

    Conference4th BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, BlackboxNLP 2021
    Country/TerritoryDominican Republic
    CityVirtual, Punta Cana
    Period11/11/21 → …

    ASJC Scopus subject areas

    • Computational Theory and Mathematics
    • Computer Science Applications
    • Information Systems

    Fingerprint

    Dive into the research topics of 'The Language Model Understood the Prompt was Ambiguous: Probing Syntactic Uncertainty Through Generation'. Together they form a unique fingerprint.

    Cite this