@inproceedings{shen-etal-2021-semi,
title = "Semi-supervised Intent Discovery with Contrastive Learning",
author = "Shen, Xiang and
Sun, Yinge and
Zhang, Yao and
Najmabadi, Mani",
editor = "Papangelis, Alexandros and
Budzianowski, Pawe{\l} and
Liu, Bing and
Nouri, Elnaz and
Rastogi, Abhinav and
Chen, Yun-Nung",
booktitle = "Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.nlp4convai-1.12",
doi = "10.18653/v1/2021.nlp4convai-1.12",
pages = "120--129",
abstract = "User intent discovery is a key step in developing a Natural Language Understanding (NLU) module at the core of any modern Conversational AI system. Typically, human experts review a representative sample of user input data to discover new intents, which is subjective, costly, and error-prone. In this work, we aim to assist the NLU developers by presenting a novel method for discovering new intents at scale given a corpus of utterances. Our method utilizes supervised contrastive learning to leverage information from a domain-relevant, already labeled dataset and identifies new intents in the corpus at hand using unsupervised K-means clustering. Our method outperforms the state-of-the-art by a large margin up to 2{\%} and 13{\%} on two benchmark datasets, measured by clustering accuracy. Furthermore, we apply our method on a large dataset from the travel domain to demonstrate its effectiveness on a real-world use case.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shen-etal-2021-semi">
<titleInfo>
<title>Semi-supervised Intent Discovery with Contrastive Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinge</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mani</namePart>
<namePart type="family">Najmabadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI</title>
</titleInfo>
<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">Paweł</namePart>
<namePart type="family">Budzianowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elnaz</namePart>
<namePart type="family">Nouri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Rastogi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</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>User intent discovery is a key step in developing a Natural Language Understanding (NLU) module at the core of any modern Conversational AI system. Typically, human experts review a representative sample of user input data to discover new intents, which is subjective, costly, and error-prone. In this work, we aim to assist the NLU developers by presenting a novel method for discovering new intents at scale given a corpus of utterances. Our method utilizes supervised contrastive learning to leverage information from a domain-relevant, already labeled dataset and identifies new intents in the corpus at hand using unsupervised K-means clustering. Our method outperforms the state-of-the-art by a large margin up to 2% and 13% on two benchmark datasets, measured by clustering accuracy. Furthermore, we apply our method on a large dataset from the travel domain to demonstrate its effectiveness on a real-world use case.</abstract>
<identifier type="citekey">shen-etal-2021-semi</identifier>
<identifier type="doi">10.18653/v1/2021.nlp4convai-1.12</identifier>
<location>
<url>https://aclanthology.org/2021.nlp4convai-1.12</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>120</start>
<end>129</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semi-supervised Intent Discovery with Contrastive Learning
%A Shen, Xiang
%A Sun, Yinge
%A Zhang, Yao
%A Najmabadi, Mani
%Y Papangelis, Alexandros
%Y Budzianowski, Paweł
%Y Liu, Bing
%Y Nouri, Elnaz
%Y Rastogi, Abhinav
%Y Chen, Yun-Nung
%S Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online
%F shen-etal-2021-semi
%X User intent discovery is a key step in developing a Natural Language Understanding (NLU) module at the core of any modern Conversational AI system. Typically, human experts review a representative sample of user input data to discover new intents, which is subjective, costly, and error-prone. In this work, we aim to assist the NLU developers by presenting a novel method for discovering new intents at scale given a corpus of utterances. Our method utilizes supervised contrastive learning to leverage information from a domain-relevant, already labeled dataset and identifies new intents in the corpus at hand using unsupervised K-means clustering. Our method outperforms the state-of-the-art by a large margin up to 2% and 13% on two benchmark datasets, measured by clustering accuracy. Furthermore, we apply our method on a large dataset from the travel domain to demonstrate its effectiveness on a real-world use case.
%R 10.18653/v1/2021.nlp4convai-1.12
%U https://aclanthology.org/2021.nlp4convai-1.12
%U https://doi.org/10.18653/v1/2021.nlp4convai-1.12
%P 120-129
Markdown (Informal)
[Semi-supervised Intent Discovery with Contrastive Learning](https://aclanthology.org/2021.nlp4convai-1.12) (Shen et al., NLP4ConvAI 2021)
ACL