Semantic Parsing for Task Oriented Dialog using Hierarchical Representations

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.

arXiv commentConference on Empirical Methods in Natural Language Processing (EMNLP) 2018

References in corpus (3)

• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
• Sequence-to-Sequence Learning as Beam-Search Optimization
• Transfer Learning for Neural Semantic Parsing

Cited by in corpus (10)

• Snorkel DryBell: A Case Study in Deploying Weak Supervision at Industrial Scale
• PyText: A Seamless Path from NLP research to production
• Automatic Discovery of Novel Intents & Domains from Text Utterances
• End-to-End Trainable Non-Collaborative Dialog System
• Building a Neural Semantic Parser from a Domain Ontology
• AutoNLU: Detecting, root-causing, and fixing NLU model errors
• X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing
• Meta learning to classify intent and slot labels with noisy few shot examples
• Multilingual Neural Semantic Parsing for Low-Resourced Languages
• Fast Intent Classification for Spoken Language Understanding