@inproceedings{chen-etal-2024-two-stage,
title = "A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent {NLU}",
author = "Chen, Guanhua and
Yao, Yutong and
Wong, Derek F. and
Chao, Lidia S.",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.157",
pages = "1778--1788",
abstract = "Multi-intent natural language understanding (NLU) presents a formidable challenge due to the model confusion arising from multiple intents within a single utterance. While previous works train the model contrastively to increase the margin between different multi-intent labels, they are less suited to the nuances of multi-intent NLU. They ignore the rich information between the shared intents, which is beneficial to constructing a better embedding space, especially in low-data scenarios. We introduce a two-stage Prediction-Aware Contrastive Learning (PACL) framework for multi-intent NLU to harness this valuable knowledge. Our approach capitalizes on shared intent information by integrating word-level pre-training and prediction-aware contrastive fine-tuning. We construct a pre-training dataset using a word-level data augmentation strategy. Subsequently, our framework dynamically assigns roles to instances during contrastive fine-tuning while introducing a prediction-aware contrastive loss to maximize the impact of contrastive learning. We present experimental results and empirical analysis conducted on three widely used datasets, demonstrating that our method surpasses the performance of three prominent baselines on both low-data and full-data scenarios.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2024-two-stage">
<titleInfo>
<title>A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLU</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guanhua</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutong</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidia</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Chao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-intent natural language understanding (NLU) presents a formidable challenge due to the model confusion arising from multiple intents within a single utterance. While previous works train the model contrastively to increase the margin between different multi-intent labels, they are less suited to the nuances of multi-intent NLU. They ignore the rich information between the shared intents, which is beneficial to constructing a better embedding space, especially in low-data scenarios. We introduce a two-stage Prediction-Aware Contrastive Learning (PACL) framework for multi-intent NLU to harness this valuable knowledge. Our approach capitalizes on shared intent information by integrating word-level pre-training and prediction-aware contrastive fine-tuning. We construct a pre-training dataset using a word-level data augmentation strategy. Subsequently, our framework dynamically assigns roles to instances during contrastive fine-tuning while introducing a prediction-aware contrastive loss to maximize the impact of contrastive learning. We present experimental results and empirical analysis conducted on three widely used datasets, demonstrating that our method surpasses the performance of three prominent baselines on both low-data and full-data scenarios.</abstract>
<identifier type="citekey">chen-etal-2024-two-stage</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.157</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1778</start>
<end>1788</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLU
%A Chen, Guanhua
%A Yao, Yutong
%A Wong, Derek F.
%A Chao, Lidia S.
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F chen-etal-2024-two-stage
%X Multi-intent natural language understanding (NLU) presents a formidable challenge due to the model confusion arising from multiple intents within a single utterance. While previous works train the model contrastively to increase the margin between different multi-intent labels, they are less suited to the nuances of multi-intent NLU. They ignore the rich information between the shared intents, which is beneficial to constructing a better embedding space, especially in low-data scenarios. We introduce a two-stage Prediction-Aware Contrastive Learning (PACL) framework for multi-intent NLU to harness this valuable knowledge. Our approach capitalizes on shared intent information by integrating word-level pre-training and prediction-aware contrastive fine-tuning. We construct a pre-training dataset using a word-level data augmentation strategy. Subsequently, our framework dynamically assigns roles to instances during contrastive fine-tuning while introducing a prediction-aware contrastive loss to maximize the impact of contrastive learning. We present experimental results and empirical analysis conducted on three widely used datasets, demonstrating that our method surpasses the performance of three prominent baselines on both low-data and full-data scenarios.
%U https://aclanthology.org/2024.lrec-main.157
%P 1778-1788
Markdown (Informal)
[A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLU](https://aclanthology.org/2024.lrec-main.157) (Chen et al., LREC-COLING 2024)
ACL