2
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Conversational Semantic Parsing for Dialog State Tracking

      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

          We consider a new perspective on dialog state tracking (DST), the task of estimating a user's goal through the course of a dialog. By formulating DST as a semantic parsing task over hierarchical representations, we can incorporate semantic compositionality, cross-domain knowledge sharing and co-reference. We present TreeDST, a dataset of 27k conversations annotated with tree-structured dialog states and system acts. We describe an encoder-decoder framework for DST with hierarchical representations, which leads to 20% improvement over state-of-the-art DST approaches that operate on a flat meaning space of slot-value pairs.

          Related collections

          Author and article information

          Journal
          24 October 2020
          Article
          2010.12770
          3a063cca-6f8d-4a50-a3b5-2dcf3696398a

          http://creativecommons.org/licenses/by-nc-sa/4.0/

          History
          Custom metadata
          Publish as a conference paper at EMNLP 2020
          cs.CL

          Theoretical computer science
          Theoretical computer science

          Comments

          Comment on this article