@inproceedings{cheng-etal-2023-mrrl,
title = "{MRRL}: Modifying the Reference via Reinforcement Learning for Non-Autoregressive Joint Multiple Intent Detection and Slot Filling",
author = "Cheng, Xuxin and
Zhu, Zhihong and
Cao, Bowen and
Ye, Qichen and
Zou, Yuexian",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.704",
doi = "10.18653/v1/2023.findings-emnlp.704",
pages = "10495--10505",
abstract = "With the rise of non-autoregressive approach, some non-autoregressive models for joint multiple intent detection and slot filling have obtained the promising inference speed. However, most existing SLU models (1) suffer from the multi-modality problem that leads to reference intents and slots may not be suitable for training; (2) lack of alignment between the correct predictions of the two tasks, which extremely limits the overall accuracy. Therefore, in this paper, we propose $\textbf{M}$odifying the $\textbf{R}$eference via $\textbf{R}$einforcement $\textbf{L}$earning (MRRL), a novel method for multiple intent detection and slot filling, which introduces a modifier and employs reinforcement learning. Specifically, we try to provide the better training target for the non-autoregressive SLU model via modifying the reference based on the output of the non-autoregressive SLU model, and propose a suitability reward to ensure that the output of the modifier module could fit well with the output of the non-autoregressive SLU model and does not deviate too far from the reference. In addition, we also propose a compromise reward to realize a flexible trade-off between the two subtasks. Experiments on two multi-intent datasets and non-autoregressive baselines demonstrate that our MRRL could consistently improve the performance of baselines. More encouragingly, our best variant achieves new state-of-the-art results, outperforming the previous best approach by 3.6 overall accuracy on MixATIS dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cheng-etal-2023-mrrl">
<titleInfo>
<title>MRRL: Modifying the Reference via Reinforcement Learning for Non-Autoregressive Joint Multiple Intent Detection and Slot Filling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuxin</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhihong</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bowen</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qichen</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuexian</namePart>
<namePart type="family">Zou</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>Findings of the Association for Computational Linguistics: EMNLP 2023</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>With the rise of non-autoregressive approach, some non-autoregressive models for joint multiple intent detection and slot filling have obtained the promising inference speed. However, most existing SLU models (1) suffer from the multi-modality problem that leads to reference intents and slots may not be suitable for training; (2) lack of alignment between the correct predictions of the two tasks, which extremely limits the overall accuracy. Therefore, in this paper, we propose Modifying the Reference via Reinforcement Learning (MRRL), a novel method for multiple intent detection and slot filling, which introduces a modifier and employs reinforcement learning. Specifically, we try to provide the better training target for the non-autoregressive SLU model via modifying the reference based on the output of the non-autoregressive SLU model, and propose a suitability reward to ensure that the output of the modifier module could fit well with the output of the non-autoregressive SLU model and does not deviate too far from the reference. In addition, we also propose a compromise reward to realize a flexible trade-off between the two subtasks. Experiments on two multi-intent datasets and non-autoregressive baselines demonstrate that our MRRL could consistently improve the performance of baselines. More encouragingly, our best variant achieves new state-of-the-art results, outperforming the previous best approach by 3.6 overall accuracy on MixATIS dataset.</abstract>
<identifier type="citekey">cheng-etal-2023-mrrl</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.704</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.704</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>10495</start>
<end>10505</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MRRL: Modifying the Reference via Reinforcement Learning for Non-Autoregressive Joint Multiple Intent Detection and Slot Filling
%A Cheng, Xuxin
%A Zhu, Zhihong
%A Cao, Bowen
%A Ye, Qichen
%A Zou, Yuexian
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F cheng-etal-2023-mrrl
%X With the rise of non-autoregressive approach, some non-autoregressive models for joint multiple intent detection and slot filling have obtained the promising inference speed. However, most existing SLU models (1) suffer from the multi-modality problem that leads to reference intents and slots may not be suitable for training; (2) lack of alignment between the correct predictions of the two tasks, which extremely limits the overall accuracy. Therefore, in this paper, we propose Modifying the Reference via Reinforcement Learning (MRRL), a novel method for multiple intent detection and slot filling, which introduces a modifier and employs reinforcement learning. Specifically, we try to provide the better training target for the non-autoregressive SLU model via modifying the reference based on the output of the non-autoregressive SLU model, and propose a suitability reward to ensure that the output of the modifier module could fit well with the output of the non-autoregressive SLU model and does not deviate too far from the reference. In addition, we also propose a compromise reward to realize a flexible trade-off between the two subtasks. Experiments on two multi-intent datasets and non-autoregressive baselines demonstrate that our MRRL could consistently improve the performance of baselines. More encouragingly, our best variant achieves new state-of-the-art results, outperforming the previous best approach by 3.6 overall accuracy on MixATIS dataset.
%R 10.18653/v1/2023.findings-emnlp.704
%U https://aclanthology.org/2023.findings-emnlp.704
%U https://doi.org/10.18653/v1/2023.findings-emnlp.704
%P 10495-10505
Markdown (Informal)
[MRRL: Modifying the Reference via Reinforcement Learning for Non-Autoregressive Joint Multiple Intent Detection and Slot Filling](https://aclanthology.org/2023.findings-emnlp.704) (Cheng et al., Findings 2023)
ACL