@inproceedings{wang-etal-2023-making,
title = "Making Pre-trained Language Models Better Learn Few-Shot Spoken Language Understanding in More Practical Scenarios",
author = "Wang, Yufan and
Mei, Jie and
Zou, Bowei and
Fan, Rui and
He, Tingting and
Aw, Ai Ti",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.853",
doi = "10.18653/v1/2023.findings-acl.853",
pages = "13508--13523",
abstract = "Most previous few-shot Spoken Language Understanding (SLU) models typically need to be trained on a set of data-rich source domains and adapt to the target domain with a few examples. In this paper, we explore a more practical scenario for few-shot SLU, in which we only assume access to a pre-trained language model and a few labeled examples without any other source domain data. We concentrate on understanding how far the few-shot SLU could be pushed in this setting. To this end, we develop a prompt-based intent detection model in few-shot settings, which leverages the BERT original pre-training next sentence prediction task and the prompt template to detect the user{'}s intent. For slot filling, we propose an approach of reconstructing slot labels, which reduces the training complexity by reducing the number of slot labels in few-shot settings. To evaluate the few-shot SLU for a more practical scenario, we present two benchmarks, FewShotATIS and FewShotSNIPS. And a dynamic sampling strategy is designed to construct the two datasets according to the learning difficulty of each intent and slot. Experiments on FewShotATIS and FewShotSNIPS demonstrate that our proposed model achieves state-of-the-art performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-making">
<titleInfo>
<title>Making Pre-trained Language Models Better Learn Few-Shot Spoken Language Understanding in More Practical Scenarios</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yufan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Mei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bowei</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tingting</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ai</namePart>
<namePart type="given">Ti</namePart>
<namePart type="family">Aw</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Most previous few-shot Spoken Language Understanding (SLU) models typically need to be trained on a set of data-rich source domains and adapt to the target domain with a few examples. In this paper, we explore a more practical scenario for few-shot SLU, in which we only assume access to a pre-trained language model and a few labeled examples without any other source domain data. We concentrate on understanding how far the few-shot SLU could be pushed in this setting. To this end, we develop a prompt-based intent detection model in few-shot settings, which leverages the BERT original pre-training next sentence prediction task and the prompt template to detect the user’s intent. For slot filling, we propose an approach of reconstructing slot labels, which reduces the training complexity by reducing the number of slot labels in few-shot settings. To evaluate the few-shot SLU for a more practical scenario, we present two benchmarks, FewShotATIS and FewShotSNIPS. And a dynamic sampling strategy is designed to construct the two datasets according to the learning difficulty of each intent and slot. Experiments on FewShotATIS and FewShotSNIPS demonstrate that our proposed model achieves state-of-the-art performance.</abstract>
<identifier type="citekey">wang-etal-2023-making</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.853</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.853</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>13508</start>
<end>13523</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Making Pre-trained Language Models Better Learn Few-Shot Spoken Language Understanding in More Practical Scenarios
%A Wang, Yufan
%A Mei, Jie
%A Zou, Bowei
%A Fan, Rui
%A He, Tingting
%A Aw, Ai Ti
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F wang-etal-2023-making
%X Most previous few-shot Spoken Language Understanding (SLU) models typically need to be trained on a set of data-rich source domains and adapt to the target domain with a few examples. In this paper, we explore a more practical scenario for few-shot SLU, in which we only assume access to a pre-trained language model and a few labeled examples without any other source domain data. We concentrate on understanding how far the few-shot SLU could be pushed in this setting. To this end, we develop a prompt-based intent detection model in few-shot settings, which leverages the BERT original pre-training next sentence prediction task and the prompt template to detect the user’s intent. For slot filling, we propose an approach of reconstructing slot labels, which reduces the training complexity by reducing the number of slot labels in few-shot settings. To evaluate the few-shot SLU for a more practical scenario, we present two benchmarks, FewShotATIS and FewShotSNIPS. And a dynamic sampling strategy is designed to construct the two datasets according to the learning difficulty of each intent and slot. Experiments on FewShotATIS and FewShotSNIPS demonstrate that our proposed model achieves state-of-the-art performance.
%R 10.18653/v1/2023.findings-acl.853
%U https://aclanthology.org/2023.findings-acl.853
%U https://doi.org/10.18653/v1/2023.findings-acl.853
%P 13508-13523
Markdown (Informal)
[Making Pre-trained Language Models Better Learn Few-Shot Spoken Language Understanding in More Practical Scenarios](https://aclanthology.org/2023.findings-acl.853) (Wang et al., Findings 2023)
ACL