Sound Natural: Content Rephrasing in Dialog Systems

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 5101–5108, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 5101 Sound Natural: Content Rephrasing in Dialog Systems Arash Einolghozati∗ Facebook arashe@fb.com Anchit Gupta∗ Facebook anchit@fb.com Keith Diedrick Facebook kdiedrick@fb.com Sonal Gupta Facebook sonalgupta@fb.com Abstract We introduce a new task of rephrasing for a more natural virtual assistant. Currently, vir- tual 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 mes- saging 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 ‘re- mind 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 with auto-regressive decoding, 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. 1 Introduction Virtual assistants have achieved very high accuracy in parsing queries for execution (Gupta et al., 2018), such as reciting the weather or setting a reminder. However, in some scenarios, parsing alone is not enough to execute a request as expected. For exam- ple, when the user says “Tell Alice I’ll meet her in 10 minutes”, executing the parsed message would send the tagged content “I’ll meet her in 10 min- utes” instead of a more appropriate message such as “I’ll meet you in 10 minutes”. The other scenario where rephrasing is needed to better represent the user’s request is when the user asks “Remind me to brush my teeth tonight”. A more natural response ∗equal contribution would be “OK, I’ll remind you to brush your teeth tonight”. To make a virtual assistant sound more natural, it needs to rephrase the user’s query content before executing it. The task is different from paraphras- ing, as we do not want to change the user’s wording, i.e., the language formality or choice of words. In- stead, we need to make minimal syntactic changes to make the utterance sound natural. As a use case, we work on the messaging domain, where we focus on rephrasing a message that needs to be inferred from the user query. This domain is so named as it covers requests about sending and receiving text and instant messages. Unlike the confirmation case, the message rephrasing is more complicated and can involve syntactic, pronoun or verb changes. Note that our goal is not to paraphrase the user’s message but to rephrase …

Content truncated to 500 words