Template Guided Text Generation for Task-Oriented Dialogue

Mihir Kale, Abhinav Rastogi


Abstract
Virtual assistants such as Google Assistant, Amazon Alexa, and Apple Siri enable users to interact with a large number of services and APIs on the web using natural language. In this work, we investigate two methods for Natural Language Generation (NLG) using a single domain-independent model across a large number of APIs. First, we propose a schema-guided approach which conditions the generation on a schema describing the API in natural language. Our second method investigates the use of a small number of templates, growing linearly in number of slots, to convey the semantics of the API. To generate utterances for an arbitrary slot combination, a few simple templates are first concatenated to give a semantically correct, but possibly incoherent and ungrammatical utterance. A pre-trained language model is subsequently employed to rewrite it into coherent, natural sounding text. Through automatic metrics and human evaluation, we show that our method improves over strong baselines, is robust to out-of-domain inputs and shows improved sample efficiency.
Anthology ID:
2020.emnlp-main.527
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6505–6520
Language:
URL:
https://aclanthology.org/2020.emnlp-main.527
DOI:
10.18653/v1/2020.emnlp-main.527
Bibkey:
Cite (ACL):
Mihir Kale and Abhinav Rastogi. 2020. Template Guided Text Generation for Task-Oriented Dialogue. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6505–6520, Online. Association for Computational Linguistics.
Cite (Informal):
Template Guided Text Generation for Task-Oriented Dialogue (Kale & Rastogi, EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.527.pdf
Video:
 https://slideslive.com/38939152
Data
E2EMultiWOZSGD