5
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Improving Semantic Parsing with Neural Generator-Reranker Architecture

      Preprint
      , ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Semantic parsing is the problem of deriving machine interpretable meaning representations from natural language utterances. Neural models with encoder-decoder architectures have recently achieved substantial improvements over traditional methods. Although neural semantic parsers appear to have relatively high recall using large beam sizes, there is room for improvement with respect to one-best precision. In this work, we propose a generator-reranker architecture for semantic parsing. The generator produces a list of potential candidates and the reranker, which consists of a pre-processing step for the candidates followed by a novel critic network, reranks these candidates based on the similarity between each candidate and the input sentence. We show the advantages of this approach along with how it improves the parsing performance through extensive analysis. We experiment our model on three semantic parsing datasets (GEO, ATIS, and OVERNIGHT). The overall architecture achieves the state-of-the-art results in all three datasets.

          Related collections

          Most cited references14

          • Record: found
          • Abstract: not found
          • Article: not found

          Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation

            Bookmark
            • Record: found
            • Abstract: not found
            • Conference Proceedings: not found

            Language to Logical Form with Neural Attention

              Bookmark
              • Record: found
              • Abstract: not found
              • Conference Proceedings: not found

              Building a Semantic Parser Overnight

                Bookmark

                Author and article information

                Journal
                27 September 2019
                Article
                1909.12764
                38ee2cdd-6195-4f4c-8f74-ab0975d19e66

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                History
                Custom metadata
                cs.CL

                Theoretical computer science
                Theoretical computer science

                Comments

                Comment on this article