Neural Semantic Parsing by Character-based Translation: Experiments with Abstract Meaning Representations

  • Rik van Noord Center for Language and Cognition Groningen (CLCG), University of Groningen, The Netherlands
  • Johan Bos Center for Language and Cognition Groningen (CLCG), University of Groningen, The Netherlands

Abstract

We evaluate the character-level translation method for neural semantic parsing on a large corpus of sentences annotated with Abstract Meaning Representations (AMRs). Using a sequence-tosequence model, and some trivial preprocessing and postprocessing of AMRs, we obtain a baseline accuracy of 53.1 (F-score on AMR-triples). We examine five different approaches to improve this baseline result: (i) reordering AMR branches to match the word order of the input sentence increases performance to 58.3; (ii) adding part-of-speech tags (automatically produced) to the input shows improvement as well (57.2); (iii) So does the introduction of super characters (conflating frequent sequences of characters to a single character), reaching 57.4; (iv) optimizing the training process by using pre-training and averaging a set of models increases performance to 58.7; (v) adding silver-standard training data obtained by an off-the-shelf parser yields the biggest improvement, resulting in an F-score of 64.0. Combining all five techniques leads to an F-score of 71.0 on holdout data, which is state-of-the-art in AMR parsing. This is remarkable because of the relative simplicity of the approach.

Published
2017-12-01
How to Cite
van Noord, R., & Bos, J. (2017). Neural Semantic Parsing by Character-based Translation: Experiments with Abstract Meaning Representations. Computational Linguistics in the Netherlands Journal, 7, 93-108. Retrieved from https://clinjournal.org/clinj/article/view/72
Section
Articles