@inproceedings{dieter-etal-2019-mimic,
title = "Mimic and Rephrase: Reflective Listening in Open-Ended Dialogue",
author = "Dieter, Justin and
Wang, Tian and
Chaganty, Arun Tejasvi and
Angeli, Gabor and
Chang, Angel X.",
editor = "Bansal, Mohit and
Villavicencio, Aline",
booktitle = "Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/K19-1037",
doi = "10.18653/v1/K19-1037",
pages = "393--403",
abstract = "Reflective listening{--}demonstrating that you have heard your conversational partner{--}is key to effective communication. Expert human communicators often mimic and rephrase their conversational partner, e.g., when responding to sentimental stories or to questions they don{'}t know the answer to. We introduce a new task and an associated dataset wherein dialogue agents similarly mimic and rephrase a user{'}s request to communicate sympathy (I{'}m sorry to hear that) or lack of knowledge (I do not know that). We study what makes a rephrasal response good against a set of qualitative metrics. We then evaluate three models for generating responses: a syntax-aware rule-based system, a seq2seq LSTM neural models with attention (S2SA), and the same neural model augmented with a copy mechanism (S2SA+C). In a human evaluation, we find that S2SA+C and the rule-based system are comparable and approach human-generated response quality. In addition, experiences with a live deployment of S2SA+C in a customer support setting suggest that this generation task is a practical contribution to real world conversational agents.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dieter-etal-2019-mimic">
<titleInfo>
<title>Mimic and Rephrase: Reflective Listening in Open-Ended Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Justin</namePart>
<namePart type="family">Dieter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tian</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arun</namePart>
<namePart type="given">Tejasvi</namePart>
<namePart type="family">Chaganty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabor</namePart>
<namePart type="family">Angeli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angel</namePart>
<namePart type="given">X</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Reflective listening–demonstrating that you have heard your conversational partner–is key to effective communication. Expert human communicators often mimic and rephrase their conversational partner, e.g., when responding to sentimental stories or to questions they don’t know the answer to. We introduce a new task and an associated dataset wherein dialogue agents similarly mimic and rephrase a user’s request to communicate sympathy (I’m sorry to hear that) or lack of knowledge (I do not know that). We study what makes a rephrasal response good against a set of qualitative metrics. We then evaluate three models for generating responses: a syntax-aware rule-based system, a seq2seq LSTM neural models with attention (S2SA), and the same neural model augmented with a copy mechanism (S2SA+C). In a human evaluation, we find that S2SA+C and the rule-based system are comparable and approach human-generated response quality. In addition, experiences with a live deployment of S2SA+C in a customer support setting suggest that this generation task is a practical contribution to real world conversational agents.</abstract>
<identifier type="citekey">dieter-etal-2019-mimic</identifier>
<identifier type="doi">10.18653/v1/K19-1037</identifier>
<location>
<url>https://aclanthology.org/K19-1037</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>393</start>
<end>403</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mimic and Rephrase: Reflective Listening in Open-Ended Dialogue
%A Dieter, Justin
%A Wang, Tian
%A Chaganty, Arun Tejasvi
%A Angeli, Gabor
%A Chang, Angel X.
%Y Bansal, Mohit
%Y Villavicencio, Aline
%S Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F dieter-etal-2019-mimic
%X Reflective listening–demonstrating that you have heard your conversational partner–is key to effective communication. Expert human communicators often mimic and rephrase their conversational partner, e.g., when responding to sentimental stories or to questions they don’t know the answer to. We introduce a new task and an associated dataset wherein dialogue agents similarly mimic and rephrase a user’s request to communicate sympathy (I’m sorry to hear that) or lack of knowledge (I do not know that). We study what makes a rephrasal response good against a set of qualitative metrics. We then evaluate three models for generating responses: a syntax-aware rule-based system, a seq2seq LSTM neural models with attention (S2SA), and the same neural model augmented with a copy mechanism (S2SA+C). In a human evaluation, we find that S2SA+C and the rule-based system are comparable and approach human-generated response quality. In addition, experiences with a live deployment of S2SA+C in a customer support setting suggest that this generation task is a practical contribution to real world conversational agents.
%R 10.18653/v1/K19-1037
%U https://aclanthology.org/K19-1037
%U https://doi.org/10.18653/v1/K19-1037
%P 393-403
Markdown (Informal)
[Mimic and Rephrase: Reflective Listening in Open-Ended Dialogue](https://aclanthology.org/K19-1037) (Dieter et al., CoNLL 2019)
ACL
- Justin Dieter, Tian Wang, Arun Tejasvi Chaganty, Gabor Angeli, and Angel X. Chang. 2019. Mimic and Rephrase: Reflective Listening in Open-Ended Dialogue. In Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pages 393–403, Hong Kong, China. Association for Computational Linguistics.