@inproceedings{mou-etal-2022-watch,
title = "Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for {OOD} Intent Discovery",
author = "Mou, Yutao and
He, Keqing and
Wang, Pei and
Wu, Yanan and
Wang, Jingang and
Wu, Wei and
Xu, Weiran",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.98",
doi = "10.18653/v1/2022.emnlp-main.98",
pages = "1517--1529",
abstract = "Discovering out-of-domain (OOD) intent is important for developing new skills in task-oriented dialogue systems. The key challenges lie in how to transfer prior in-domain (IND) knowledge to OOD clustering, as well as jointly learn OOD representations and cluster assignments. Previous methods suffer from in-domain overfitting problem, and there is a natural gap between representation learning and clustering objectives. In this paper, we propose a unified K-nearest neighbor contrastive learning framework to discover OOD intents. Specifically, for IND pre-training stage, we propose a KCL objective to learn inter-class discriminative features, while maintaining intra-class diversity, which alleviates the in-domain overfitting problem. For OOD clustering stage, we propose a KCC method to form compact clusters by mining true hard negative samples, which bridges the gap between clustering and representation learning. Extensive experiments on three benchmark datasets show that our method achieves substantial improvements over the state-of-the-art methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mou-etal-2022-watch">
<titleInfo>
<title>Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discovery</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yutao</namePart>
<namePart type="family">Mou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keqing</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanan</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiran</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Discovering out-of-domain (OOD) intent is important for developing new skills in task-oriented dialogue systems. The key challenges lie in how to transfer prior in-domain (IND) knowledge to OOD clustering, as well as jointly learn OOD representations and cluster assignments. Previous methods suffer from in-domain overfitting problem, and there is a natural gap between representation learning and clustering objectives. In this paper, we propose a unified K-nearest neighbor contrastive learning framework to discover OOD intents. Specifically, for IND pre-training stage, we propose a KCL objective to learn inter-class discriminative features, while maintaining intra-class diversity, which alleviates the in-domain overfitting problem. For OOD clustering stage, we propose a KCC method to form compact clusters by mining true hard negative samples, which bridges the gap between clustering and representation learning. Extensive experiments on three benchmark datasets show that our method achieves substantial improvements over the state-of-the-art methods.</abstract>
<identifier type="citekey">mou-etal-2022-watch</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.98</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.98</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>1517</start>
<end>1529</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discovery
%A Mou, Yutao
%A He, Keqing
%A Wang, Pei
%A Wu, Yanan
%A Wang, Jingang
%A Wu, Wei
%A Xu, Weiran
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F mou-etal-2022-watch
%X Discovering out-of-domain (OOD) intent is important for developing new skills in task-oriented dialogue systems. The key challenges lie in how to transfer prior in-domain (IND) knowledge to OOD clustering, as well as jointly learn OOD representations and cluster assignments. Previous methods suffer from in-domain overfitting problem, and there is a natural gap between representation learning and clustering objectives. In this paper, we propose a unified K-nearest neighbor contrastive learning framework to discover OOD intents. Specifically, for IND pre-training stage, we propose a KCL objective to learn inter-class discriminative features, while maintaining intra-class diversity, which alleviates the in-domain overfitting problem. For OOD clustering stage, we propose a KCC method to form compact clusters by mining true hard negative samples, which bridges the gap between clustering and representation learning. Extensive experiments on three benchmark datasets show that our method achieves substantial improvements over the state-of-the-art methods.
%R 10.18653/v1/2022.emnlp-main.98
%U https://aclanthology.org/2022.emnlp-main.98
%U https://doi.org/10.18653/v1/2022.emnlp-main.98
%P 1517-1529
Markdown (Informal)
[Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discovery](https://aclanthology.org/2022.emnlp-main.98) (Mou et al., EMNLP 2022)
ACL