Analyzing and Interpreting Neural Networks for NLP: A Report on the First BlackboxNLP Workshop

    Research output: Contribution to journalArticleScientific

    Abstract

    The Empirical Methods in Natural Language Processing (EMNLP) 2018 workshop BlackboxNLP was dedicated to resources and techniques specifically developed for analyzing and understanding the inner-workings and representations acquired by neural models of language. Approaches included: systematic manipulation of input to neural networks and investigating the impact on their performance, testing whether interpretable knowledge can be decoded from intermediate representations acquired by neural networks, proposing modifications to neural network architectures to make their knowledge state or generated output more explainable, and examining the performance of networks on simplified or formal languages. Here we review a number of representative studies in each category.

    Original languageEnglish
    Article number135132491900024
    Pages (from-to)543-557
    Number of pages15
    JournalNatural Language Engineering
    Volume25
    Issue number4
    DOIs
    Publication statusPublished - 31 Jul 2019
    Event2018 EMNLP BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP - Brussels, Belgium
    Duration: 1 Nov 20181 Nov 2018
    Conference number: 1
    https://blackboxnlp.github.io/2018/

    Keywords

    • RECURRENT
    • interpretability
    • natural language processing
    • neural networks

    Fingerprint

    Dive into the research topics of 'Analyzing and Interpreting Neural Networks for NLP: A Report on the First BlackboxNLP Workshop'. Together they form a unique fingerprint.

    Cite this