Discrete representations in neural models of spoken language

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

    Abstract

    The distributed and continuous representations used by neural networks are at odds with representations employed in linguistics, which are typically symbolic. Vector quantization has been proposed as a way to induce discrete neural representations that are closer in nature to their linguistic counterparts. However, it is not clear which metrics are the best-suited to analyze such discrete representations. We compare the merits of four commonly used metrics in the context of weakly supervised models of spoken language. We compare the results they show when applied to two different models, while systematically studying the effect of the placement and size of the discretization layer. We find that different evaluation regimes can give inconsistent results. While we can attribute them to the properties of the different metrics in most cases, one point of concern remains: the use of minimal pairs of phoneme triples as stimuli disadvantages larger discrete unit inventories, unlike metrics applied to complete utterances. Furthermore, while in general vector quantization induces representations that correlate with units posited in linguistics, the strength of this correlation is only moderate.
    Original languageEnglish
    Title of host publicationProceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
    PublisherAssociation for Computational Linguistics
    Pages163-176
    Number of pages14
    ISBN (Electronic)9781955917063
    DOIs
    Publication statusPublished - 1 Nov 2021
    EventBlackboxNLP 2021: Analyzing and Interpreting Neural Networks for NLP - online
    Duration: 11 Nov 202111 Nov 2021
    https://blackboxnlp.github.io/2021/

    Workshop

    WorkshopBlackboxNLP 2021
    Abbreviated titleBlackboxNLP2021
    Period11/11/2111/11/21
    Internet address

    Fingerprint

    Dive into the research topics of 'Discrete representations in neural models of spoken language'. Together they form a unique fingerprint.

    Cite this