@inproceedings{chen-etal-2020-automating,
title = "Automating Template Creation for Ranking-Based Dialogue Models",
author = "Chen, Jingxiang and
Elfardy, Heba and
Wang, Simi and
Kahn, Andrea and
Kramer, Jared",
editor = "Wen, Tsung-Hsien and
Celikyilmaz, Asli and
Yu, Zhou and
Papangelis, Alexandros and
Eric, Mihail and
Kumar, Anuj and
Casanueva, I{\~n}igo and
Shah, Rushin",
booktitle = "Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.nlp4convai-1.9",
doi = "10.18653/v1/2020.nlp4convai-1.9",
pages = "71--78",
abstract = "Dialogue response generation models that use template ranking rather than direct sequence generation allow model developers to limit generated responses to pre-approved messages. However, manually creating templates is time-consuming and requires domain expertise. To alleviate this problem, we explore automating the process of creating dialogue templates by using unsupervised methods to cluster historical utterances and selecting representative utterances from each cluster. Specifically, we propose an end-to-end model called Deep Sentence Encoder Clustering (DSEC) that uses an auto-encoder structure to jointly learn the utterance representation and construct template clusters. We compare this method to a random baseline that randomly assigns templates to clusters as well as a strong baseline that performs the sentence encoding and the utterance clustering sequentially. To evaluate the performance of the proposed method, we perform an automatic evaluation with two annotated customer service datasets to assess clustering effectiveness, and a human-in-the-loop experiment using a live customer service application to measure the acceptance rate of the generated templates. DSEC performs best in the automatic evaluation, beats both the sequential and random baselines on most metrics in the human-in-the-loop experiment, and shows promising results when compared to gold/manually created templates.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2020-automating">
<titleInfo>
<title>Automating Template Creation for Ranking-Based Dialogue Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jingxiang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heba</namePart>
<namePart type="family">Elfardy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Kahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jared</namePart>
<namePart type="family">Kramer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tsung-Hsien</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Celikyilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandros</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihail</namePart>
<namePart type="family">Eric</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anuj</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iñigo</namePart>
<namePart type="family">Casanueva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rushin</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Dialogue response generation models that use template ranking rather than direct sequence generation allow model developers to limit generated responses to pre-approved messages. However, manually creating templates is time-consuming and requires domain expertise. To alleviate this problem, we explore automating the process of creating dialogue templates by using unsupervised methods to cluster historical utterances and selecting representative utterances from each cluster. Specifically, we propose an end-to-end model called Deep Sentence Encoder Clustering (DSEC) that uses an auto-encoder structure to jointly learn the utterance representation and construct template clusters. We compare this method to a random baseline that randomly assigns templates to clusters as well as a strong baseline that performs the sentence encoding and the utterance clustering sequentially. To evaluate the performance of the proposed method, we perform an automatic evaluation with two annotated customer service datasets to assess clustering effectiveness, and a human-in-the-loop experiment using a live customer service application to measure the acceptance rate of the generated templates. DSEC performs best in the automatic evaluation, beats both the sequential and random baselines on most metrics in the human-in-the-loop experiment, and shows promising results when compared to gold/manually created templates.</abstract>
<identifier type="citekey">chen-etal-2020-automating</identifier>
<identifier type="doi">10.18653/v1/2020.nlp4convai-1.9</identifier>
<location>
<url>https://aclanthology.org/2020.nlp4convai-1.9</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>71</start>
<end>78</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automating Template Creation for Ranking-Based Dialogue Models
%A Chen, Jingxiang
%A Elfardy, Heba
%A Wang, Simi
%A Kahn, Andrea
%A Kramer, Jared
%Y Wen, Tsung-Hsien
%Y Celikyilmaz, Asli
%Y Yu, Zhou
%Y Papangelis, Alexandros
%Y Eric, Mihail
%Y Kumar, Anuj
%Y Casanueva, Iñigo
%Y Shah, Rushin
%S Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F chen-etal-2020-automating
%X Dialogue response generation models that use template ranking rather than direct sequence generation allow model developers to limit generated responses to pre-approved messages. However, manually creating templates is time-consuming and requires domain expertise. To alleviate this problem, we explore automating the process of creating dialogue templates by using unsupervised methods to cluster historical utterances and selecting representative utterances from each cluster. Specifically, we propose an end-to-end model called Deep Sentence Encoder Clustering (DSEC) that uses an auto-encoder structure to jointly learn the utterance representation and construct template clusters. We compare this method to a random baseline that randomly assigns templates to clusters as well as a strong baseline that performs the sentence encoding and the utterance clustering sequentially. To evaluate the performance of the proposed method, we perform an automatic evaluation with two annotated customer service datasets to assess clustering effectiveness, and a human-in-the-loop experiment using a live customer service application to measure the acceptance rate of the generated templates. DSEC performs best in the automatic evaluation, beats both the sequential and random baselines on most metrics in the human-in-the-loop experiment, and shows promising results when compared to gold/manually created templates.
%R 10.18653/v1/2020.nlp4convai-1.9
%U https://aclanthology.org/2020.nlp4convai-1.9
%U https://doi.org/10.18653/v1/2020.nlp4convai-1.9
%P 71-78
Markdown (Informal)
[Automating Template Creation for Ranking-Based Dialogue Models](https://aclanthology.org/2020.nlp4convai-1.9) (Chen et al., NLP4ConvAI 2020)
ACL