Sound Natural: Content Rephrasing in Dialog Systems

Arash Einolghozati, Anchit Gupta, Keith Diedrick, Sonal Gupta


Abstract
We introduce a new task of rephrasing for a more natural virtual assistant. Currently, virtual assistants work in the paradigm of intent-slot tagging and the slot values are directly passed as-is to the execution engine. However, this setup fails in some scenarios such as messaging when the query given by the user needs to be changed before repeating it or sending it to another user. For example, for queries like ‘ask my wife if she can pick up the kids’ or ‘remind me to take my pills’, we need to rephrase the content to ‘can you pick up the kids’ and ‘take your pills’. In this paper, we study the problem of rephrasing with messaging as a use case and release a dataset of 3000 pairs of original query and rephrased query. We show that BART, a pre-trained transformers-based masked language model, is a strong baseline for the task, and show improvements by adding a copy-pointer and copy loss to it. We analyze different trade-offs of BART-based and LSTM-based seq2seq models, and propose a distilled LSTM-based seq2seq as the best practical model
Anthology ID:
2020.emnlp-main.414
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5101–5108
Language:
URL:
https://www.aclweb.org/anthology/2020.emnlp-main.414
DOI:
10.18653/v1/2020.emnlp-main.414
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.emnlp-main.414.pdf