@inproceedings{singhal-etal-2023-intendd,
title = "{I}nten{DD}: A Unified Contrastive Learning Approach for Intent Detection and Discovery",
author = "Singhal, Bhavuk and
Gupta, Ashim and
Shivasankaran, V P and
Krishna, Amrith",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.947",
doi = "10.18653/v1/2023.findings-emnlp.947",
pages = "14204--14216",
abstract = "Identifying intents from dialogue utterances forms an integral component of task-oriented dialogue systems. Intent-related tasks are typically formulated either as a classification task, where the utterances are classified into predefined categories or as a clustering task when new and previously unknown intent categories need to be discovered from these utterances. Further, the intent classification may be modeled in a multiclass (MC) or multilabel (ML) setup. While typically these tasks are modeled as separate tasks, we propose IntenDD a unified approach leveraging a shared utterance encoding backbone. IntenDD uses an entirely unsupervised contrastive learning strategy for representation learning, where pseudo-labels for the unlabeled utterances are generated based on their lexical features. Additionally, we introduce a two-step post-processing setup for the classification tasks using modified adsorption. Here, first, the residuals in the training data are propagated followed by smoothing the labels both modeled in a transductive setting. Through extensive evaluations on various benchmark datasets, we find that our approach consistently outperforms competitive baselines across all three tasks. On average, IntenDD reports percentage improvements of 2.32 {\%}, 1.26 {\%}, and 1.52 {\%} in their respective metrics for few-shot MC, few-shot ML, and the intent discovery tasks respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singhal-etal-2023-intendd">
<titleInfo>
<title>IntenDD: A Unified Contrastive Learning Approach for Intent Detection and Discovery</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bhavuk</namePart>
<namePart type="family">Singhal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashim</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">V</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Shivasankaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amrith</namePart>
<namePart type="family">Krishna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Identifying intents from dialogue utterances forms an integral component of task-oriented dialogue systems. Intent-related tasks are typically formulated either as a classification task, where the utterances are classified into predefined categories or as a clustering task when new and previously unknown intent categories need to be discovered from these utterances. Further, the intent classification may be modeled in a multiclass (MC) or multilabel (ML) setup. While typically these tasks are modeled as separate tasks, we propose IntenDD a unified approach leveraging a shared utterance encoding backbone. IntenDD uses an entirely unsupervised contrastive learning strategy for representation learning, where pseudo-labels for the unlabeled utterances are generated based on their lexical features. Additionally, we introduce a two-step post-processing setup for the classification tasks using modified adsorption. Here, first, the residuals in the training data are propagated followed by smoothing the labels both modeled in a transductive setting. Through extensive evaluations on various benchmark datasets, we find that our approach consistently outperforms competitive baselines across all three tasks. On average, IntenDD reports percentage improvements of 2.32 %, 1.26 %, and 1.52 % in their respective metrics for few-shot MC, few-shot ML, and the intent discovery tasks respectively.</abstract>
<identifier type="citekey">singhal-etal-2023-intendd</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.947</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.947</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>14204</start>
<end>14216</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IntenDD: A Unified Contrastive Learning Approach for Intent Detection and Discovery
%A Singhal, Bhavuk
%A Gupta, Ashim
%A Shivasankaran, V. P.
%A Krishna, Amrith
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F singhal-etal-2023-intendd
%X Identifying intents from dialogue utterances forms an integral component of task-oriented dialogue systems. Intent-related tasks are typically formulated either as a classification task, where the utterances are classified into predefined categories or as a clustering task when new and previously unknown intent categories need to be discovered from these utterances. Further, the intent classification may be modeled in a multiclass (MC) or multilabel (ML) setup. While typically these tasks are modeled as separate tasks, we propose IntenDD a unified approach leveraging a shared utterance encoding backbone. IntenDD uses an entirely unsupervised contrastive learning strategy for representation learning, where pseudo-labels for the unlabeled utterances are generated based on their lexical features. Additionally, we introduce a two-step post-processing setup for the classification tasks using modified adsorption. Here, first, the residuals in the training data are propagated followed by smoothing the labels both modeled in a transductive setting. Through extensive evaluations on various benchmark datasets, we find that our approach consistently outperforms competitive baselines across all three tasks. On average, IntenDD reports percentage improvements of 2.32 %, 1.26 %, and 1.52 % in their respective metrics for few-shot MC, few-shot ML, and the intent discovery tasks respectively.
%R 10.18653/v1/2023.findings-emnlp.947
%U https://aclanthology.org/2023.findings-emnlp.947
%U https://doi.org/10.18653/v1/2023.findings-emnlp.947
%P 14204-14216
Markdown (Informal)
[IntenDD: A Unified Contrastive Learning Approach for Intent Detection and Discovery](https://aclanthology.org/2023.findings-emnlp.947) (Singhal et al., Findings 2023)
ACL