Exploring Neural Methods for Parsing Discourse Representation Structures

    OnderzoeksoutputAcademicpeer review

    274 Downloads (Pure)


    Neural methods have had several recent successes in semantic parsing, though they have yet to face the challenge of producing meaning representations based on formal semantics. We present a sequence-to-sequence neural semantic parser that is able to produce Discourse Representation Structures (DRSs) for English sentences with high accuracy, outperforming traditional DRS parsers. To facilitate the learning of the output, we represent DRSs as a sequence of flat clauses and introduce a method to verify that produced DRSs are well-formed and interpretable. We compare models using characters and words as input and see (somewhat surprisingly) that the former performs better than the latter. We show that eliminating variable names from the output using De Bruijn indices increases parser performance. Adding silver training data boosts performance even further.
    Originele taal-2English
    Pagina's (van-tot)619-633
    Aantal pagina's15
    TijdschriftTransactions of the Association for Computational Linguistics
    StatusPublished - 2018

    Citeer dit