@inproceedings{sung-etal-2023-pre,
title = "Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification",
author = "Sung, Mujeen and
Gung, James and
Mansimov, Elman and
Pappas, Nikolaos and
Shu, Raphael and
Romeo, Salvatore and
Zhang, Yi and
Castelli, Vittorio",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.646",
doi = "10.18653/v1/2023.emnlp-main.646",
pages = "10433--10442",
abstract = "Intent classification (IC) plays an important role in task-oriented dialogue systems. However, IC models often generalize poorly when training without sufficient annotated examples for each user intent. We propose a novel pre-training method for text encoders that uses contrastive learning with intent psuedo-labels to produce embeddings that are well-suited for IC tasks, reducing the need for manual annotations. By applying this pre-training strategy, we also introduce Pre-trained Intent-aware Encoder (PIE), which is designed to align encodings of utterances with their intent names. Specifically, we first train a tagger to identify key phrases within utterances that are crucial for interpreting intents. We then use these extracted phrases to create examples for pre-training a text encoder in a contrastive manner. As a result, our PIE model achieves up to 5.4{\%} and 4.0{\%} higher accuracy than the previous state-of-the-art pre-trained text encoder for the N-way zero- and one-shot settings on four IC datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sung-etal-2023-pre">
<titleInfo>
<title>Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mujeen</namePart>
<namePart type="family">Sung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Gung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elman</namePart>
<namePart type="family">Mansimov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Pappas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raphael</namePart>
<namePart type="family">Shu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salvatore</namePart>
<namePart type="family">Romeo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vittorio</namePart>
<namePart type="family">Castelli</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>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</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>Intent classification (IC) plays an important role in task-oriented dialogue systems. However, IC models often generalize poorly when training without sufficient annotated examples for each user intent. We propose a novel pre-training method for text encoders that uses contrastive learning with intent psuedo-labels to produce embeddings that are well-suited for IC tasks, reducing the need for manual annotations. By applying this pre-training strategy, we also introduce Pre-trained Intent-aware Encoder (PIE), which is designed to align encodings of utterances with their intent names. Specifically, we first train a tagger to identify key phrases within utterances that are crucial for interpreting intents. We then use these extracted phrases to create examples for pre-training a text encoder in a contrastive manner. As a result, our PIE model achieves up to 5.4% and 4.0% higher accuracy than the previous state-of-the-art pre-trained text encoder for the N-way zero- and one-shot settings on four IC datasets.</abstract>
<identifier type="citekey">sung-etal-2023-pre</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.646</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.646</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>10433</start>
<end>10442</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification
%A Sung, Mujeen
%A Gung, James
%A Mansimov, Elman
%A Pappas, Nikolaos
%A Shu, Raphael
%A Romeo, Salvatore
%A Zhang, Yi
%A Castelli, Vittorio
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F sung-etal-2023-pre
%X Intent classification (IC) plays an important role in task-oriented dialogue systems. However, IC models often generalize poorly when training without sufficient annotated examples for each user intent. We propose a novel pre-training method for text encoders that uses contrastive learning with intent psuedo-labels to produce embeddings that are well-suited for IC tasks, reducing the need for manual annotations. By applying this pre-training strategy, we also introduce Pre-trained Intent-aware Encoder (PIE), which is designed to align encodings of utterances with their intent names. Specifically, we first train a tagger to identify key phrases within utterances that are crucial for interpreting intents. We then use these extracted phrases to create examples for pre-training a text encoder in a contrastive manner. As a result, our PIE model achieves up to 5.4% and 4.0% higher accuracy than the previous state-of-the-art pre-trained text encoder for the N-way zero- and one-shot settings on four IC datasets.
%R 10.18653/v1/2023.emnlp-main.646
%U https://aclanthology.org/2023.emnlp-main.646
%U https://doi.org/10.18653/v1/2023.emnlp-main.646
%P 10433-10442
Markdown (Informal)
[Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification](https://aclanthology.org/2023.emnlp-main.646) (Sung et al., EMNLP 2023)
ACL