@inproceedings{arora-etal-2024-universlu,
title = "{U}niver{SLU}: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions",
author = "Arora, Siddhant and
Futami, Hayato and
Jung, Jee-weon and
Peng, Yifan and
Sharma, Roshan and
Kashiwagi, Yosuke and
Tsunoo, Emiru and
Livescu, Karen and
Watanabe, Shinji",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.151",
doi = "10.18653/v1/2024.naacl-long.151",
pages = "2754--2774",
abstract = "Recent studies leverage large language models with multi-tasking capabilities, using natural language prompts to guide the model{'}s behavior and surpassing performance of task-specific models. Motivated by this, we ask: can we build a single model that jointly performs various spoken language understanding (SLU) tasks? We start by adapting a pre-trained automatic speech recognition model to additional tasks using single-token task specifiers. We enhance this approach through instruction tuning, i.e., finetuning by describing the task using natural language instructions followed by the list of label options. Our approach can generalize to new task descriptions for the seen tasks during inference, thereby enhancing its user-friendliness. We demonstrate the efficacy of our single multi-task learning model {``}UniverSLU{''} for 12 speech classification and sequence generation task types spanning 17 datasets and 9 languages. On most tasks, UniverSLU achieves competitive performance and often even surpasses task-specific models. Additionally, we assess the zero-shot capabilities, finding that the model generalizes to new datasets and languages for seen task types.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arora-etal-2024-universlu">
<titleInfo>
<title>UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siddhant</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hayato</namePart>
<namePart type="family">Futami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jee-weon</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roshan</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yosuke</namePart>
<namePart type="family">Kashiwagi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emiru</namePart>
<namePart type="family">Tsunoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">Livescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shinji</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent studies leverage large language models with multi-tasking capabilities, using natural language prompts to guide the model’s behavior and surpassing performance of task-specific models. Motivated by this, we ask: can we build a single model that jointly performs various spoken language understanding (SLU) tasks? We start by adapting a pre-trained automatic speech recognition model to additional tasks using single-token task specifiers. We enhance this approach through instruction tuning, i.e., finetuning by describing the task using natural language instructions followed by the list of label options. Our approach can generalize to new task descriptions for the seen tasks during inference, thereby enhancing its user-friendliness. We demonstrate the efficacy of our single multi-task learning model “UniverSLU” for 12 speech classification and sequence generation task types spanning 17 datasets and 9 languages. On most tasks, UniverSLU achieves competitive performance and often even surpasses task-specific models. Additionally, we assess the zero-shot capabilities, finding that the model generalizes to new datasets and languages for seen task types.</abstract>
<identifier type="citekey">arora-etal-2024-universlu</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.151</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.151</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>2754</start>
<end>2774</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions
%A Arora, Siddhant
%A Futami, Hayato
%A Jung, Jee-weon
%A Peng, Yifan
%A Sharma, Roshan
%A Kashiwagi, Yosuke
%A Tsunoo, Emiru
%A Livescu, Karen
%A Watanabe, Shinji
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F arora-etal-2024-universlu
%X Recent studies leverage large language models with multi-tasking capabilities, using natural language prompts to guide the model’s behavior and surpassing performance of task-specific models. Motivated by this, we ask: can we build a single model that jointly performs various spoken language understanding (SLU) tasks? We start by adapting a pre-trained automatic speech recognition model to additional tasks using single-token task specifiers. We enhance this approach through instruction tuning, i.e., finetuning by describing the task using natural language instructions followed by the list of label options. Our approach can generalize to new task descriptions for the seen tasks during inference, thereby enhancing its user-friendliness. We demonstrate the efficacy of our single multi-task learning model “UniverSLU” for 12 speech classification and sequence generation task types spanning 17 datasets and 9 languages. On most tasks, UniverSLU achieves competitive performance and often even surpasses task-specific models. Additionally, we assess the zero-shot capabilities, finding that the model generalizes to new datasets and languages for seen task types.
%R 10.18653/v1/2024.naacl-long.151
%U https://aclanthology.org/2024.naacl-long.151
%U https://doi.org/10.18653/v1/2024.naacl-long.151
%P 2754-2774
Markdown (Informal)
[UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions](https://aclanthology.org/2024.naacl-long.151) (Arora et al., NAACL 2024)
ACL
- Siddhant Arora, Hayato Futami, Jee-weon Jung, Yifan Peng, Roshan Sharma, Yosuke Kashiwagi, Emiru Tsunoo, Karen Livescu, and Shinji Watanabe. 2024. UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 2754–2774, Mexico City, Mexico. Association for Computational Linguistics.