@inproceedings{fan-etal-2024-lanid-llm,
title = "{LANID}: {LLM}-assisted New Intent Discovery",
author = "Fan, Lu and
Pu, Jiashu and
Zhang, Rongsheng and
Wu, Xiao-Ming",
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.883",
pages = "10110--10116",
abstract = "Data annotation is expensive in Task-Oriented Dialogue (TOD) systems. New Intent Discovery (NID) is a task aims to identify novel intents while retaining the ability to recognize known intents. It is essential for expanding the intent base of task-based dialogue systems. Previous works relying on external datasets are hardly extendable. Meanwhile, the effective ones are generally depends on the power of the Large Language Models (LLMs). To address the limitation of model extensibility and take advantages of LLMs for the NID task, we propose LANID, a framework that leverages LLM{'}s zero-shot capability to enhance the performance of a smaller text encoder on the NID task. LANID employs KNN and DBSCAN algorithms to select appropriate pairs of utterances from the training set. The LLM is then asked to determine the relationships between them. The collected data are then used to construct finetuning task and the small text encoder is optimized with a triplet loss. Our experimental results demonstrate the efficacy of the proposed method on three distinct NID datasets, surpassing all strong baselines in both unsupervised and semi-supervised settings. Our code can be found in https://github.com/floatSDSDS/LANID.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fan-etal-2024-lanid-llm">
<titleInfo>
<title>LANID: LLM-assisted New Intent Discovery</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiashu</namePart>
<namePart type="family">Pu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rongsheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao-Ming</namePart>
<namePart type="family">Wu</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>Data annotation is expensive in Task-Oriented Dialogue (TOD) systems. New Intent Discovery (NID) is a task aims to identify novel intents while retaining the ability to recognize known intents. It is essential for expanding the intent base of task-based dialogue systems. Previous works relying on external datasets are hardly extendable. Meanwhile, the effective ones are generally depends on the power of the Large Language Models (LLMs). To address the limitation of model extensibility and take advantages of LLMs for the NID task, we propose LANID, a framework that leverages LLM’s zero-shot capability to enhance the performance of a smaller text encoder on the NID task. LANID employs KNN and DBSCAN algorithms to select appropriate pairs of utterances from the training set. The LLM is then asked to determine the relationships between them. The collected data are then used to construct finetuning task and the small text encoder is optimized with a triplet loss. Our experimental results demonstrate the efficacy of the proposed method on three distinct NID datasets, surpassing all strong baselines in both unsupervised and semi-supervised settings. Our code can be found in https://github.com/floatSDSDS/LANID.</abstract>
<identifier type="citekey">fan-etal-2024-lanid-llm</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.883</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>10110</start>
<end>10116</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LANID: LLM-assisted New Intent Discovery
%A Fan, Lu
%A Pu, Jiashu
%A Zhang, Rongsheng
%A Wu, Xiao-Ming
%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 fan-etal-2024-lanid-llm
%X Data annotation is expensive in Task-Oriented Dialogue (TOD) systems. New Intent Discovery (NID) is a task aims to identify novel intents while retaining the ability to recognize known intents. It is essential for expanding the intent base of task-based dialogue systems. Previous works relying on external datasets are hardly extendable. Meanwhile, the effective ones are generally depends on the power of the Large Language Models (LLMs). To address the limitation of model extensibility and take advantages of LLMs for the NID task, we propose LANID, a framework that leverages LLM’s zero-shot capability to enhance the performance of a smaller text encoder on the NID task. LANID employs KNN and DBSCAN algorithms to select appropriate pairs of utterances from the training set. The LLM is then asked to determine the relationships between them. The collected data are then used to construct finetuning task and the small text encoder is optimized with a triplet loss. Our experimental results demonstrate the efficacy of the proposed method on three distinct NID datasets, surpassing all strong baselines in both unsupervised and semi-supervised settings. Our code can be found in https://github.com/floatSDSDS/LANID.
%U https://aclanthology.org/2024.lrec-main.883
%P 10110-10116
Markdown (Informal)
[LANID: LLM-assisted New Intent Discovery](https://aclanthology.org/2024.lrec-main.883) (Fan et al., LREC-COLING 2024)
ACL
- Lu Fan, Jiashu Pu, Rongsheng Zhang, and Xiao-Ming Wu. 2024. LANID: LLM-assisted New Intent Discovery. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 10110–10116, Torino, Italia. ELRA and ICCL.