Semantic Parsing for Task Oriented Dialog using Hierarchical Representations

TL;DR

This paper introduces a hierarchical semantic parsing scheme for task-oriented dialog systems, enabling the modeling of complex compositional queries with improved parsing accuracy over sequence-to-sequence models.

Contribution

It proposes a novel hierarchical annotation scheme for semantic parsing that captures compositional queries and demonstrates its effectiveness with a new dataset and improved parsing results.

Findings

Hierarchical scheme effectively models complex queries.

Parsing models outperform sequence-to-sequence approaches.

New dataset of 44k annotated queries released.

Abstract

Task oriented dialog systems typically first parse user utterances to semantic frames comprised of intents and slots. Previous work on task oriented intent and slot-filling work has been restricted to one intent per query and one slot label per token, and thus cannot model complex compositional requests. Alternative semantic parsing systems have represented queries as logical forms, but these are challenging to annotate and parse. We propose a hierarchical annotation scheme for semantic parsing that allows the representation of compositional queries, and can be efficiently and accurately parsed by standard constituency parsing models. We release a dataset of 44k annotated queries (fb.me/semanticparsingdialog), and show that parsing models outperform sequence-to-sequence approaches on this dataset.