Compositional Task-Oriented Parsing as Abstractive Question Answering
Wenting Zhao, Konstantine Arkoudas, Weiqi Sun, Claire Cardie
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 seq2seq2 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.
BibTeX
@inproceedings{zhao-etal-2022-compositional,
title = "Compositional Task-Oriented Parsing as Abstractive Question Answering",
author = "Zhao, Wenting and
Arkoudas, Konstantine and
Sun, Weiqi and
Cardie, Claire",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.328/",
doi = "10.18653/v1/2022.naacl-main.328",
pages = "4418--4427"
}