Compositional Task-Oriented Parsing as Abstractive Question Answering

TL;DR

This paper presents a novel approach to task-oriented parsing by reducing it to abstractive question answering, leading to improved performance especially in low-data scenarios.

Contribution

It introduces a QA-based method for naturalized semantic parsing that overcomes limitations of canonical paraphrasing and outperforms existing methods.

Findings

Outperforms state-of-the-art in full-data settings

Achieves significant improvements in few-shot learning

Demonstrates effectiveness of QA-based parsing approach

Abstract

Task-oriented parsing (TOP) aims to convert natural language into machine-readable representations of specific tasks, such as setting an alarm. A popular approach to TOP is to apply seq2seq models to generate linearized parse trees. A more recent line of work argues that pretrained seq2seq models are better at generating outputs that are themselves natural language, so they replace linearized parse trees with canonical natural-language paraphrases that can then be easily translated into parse trees, resulting in so-called naturalized parsers. In this work we continue to explore naturalized semantic parsing by presenting a general reduction of TOP to abstractive question answering that overcomes some limitations of canonical paraphrasing. Experimental results show that our QA-based technique outperforms state-of-the-art methods in full-data settings while achieving dramatic improvements in few-shot settings.