@inproceedings{huang-etal-2022-mtl,
title = "{MTL}-{SLT}: Multi-Task Learning for Spoken Language Tasks",
author = "Huang, Zhiqi and
Rao, Milind and
Raju, Anirudh and
Zhang, Zhe and
Bui, Bach and
Lee, Chul",
editor = "Liu, Bing and
Papangelis, Alexandros and
Ultes, Stefan and
Rastogi, Abhinav and
Chen, Yun-Nung and
Spithourakis, Georgios and
Nouri, Elnaz and
Shi, Weiyan",
booktitle = "Proceedings of the 4th Workshop on NLP for Conversational AI",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.nlp4convai-1.11",
doi = "10.18653/v1/2022.nlp4convai-1.11",
pages = "120--130",
abstract = "Language understanding in speech-based systems has attracted extensive interest from both academic and industrial communities in recent years with the growing demand for voice-based applications. Prior works focus on independent research by the automatic speech recognition (ASR) and natural language processing (NLP) communities, or on jointly modeling the speech and NLP problems focusing on a single dataset or single NLP task. To facilitate the development of spoken language research, we introduce MTL-SLT, a multi-task learning framework for spoken language tasks. MTL-SLT takes speech as input, and outputs transcription, intent, named entities, summaries, and answers to text queries, supporting the tasks of spoken language understanding, spoken summarization and spoken question answering respectively. The proposed framework benefits from three key aspects: 1) pre-trained sub-networks of ASR model and language model; 2) multi-task learning objective to exploit shared knowledge from different tasks; 3) end-to-end training of ASR and downstream NLP task based on sequence loss. We obtain state-of-the-art results on spoken language understanding tasks such as SLURP and ATIS. Spoken summarization results are reported on a new dataset: Spoken-Gigaword.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2022-mtl">
<titleInfo>
<title>MTL-SLT: Multi-Task Learning for Spoken Language Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhiqi</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milind</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anirudh</namePart>
<namePart type="family">Raju</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhe</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bach</namePart>
<namePart type="family">Bui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chul</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on NLP for Conversational AI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandros</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Ultes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Rastogi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georgios</namePart>
<namePart type="family">Spithourakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elnaz</namePart>
<namePart type="family">Nouri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiyan</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Language understanding in speech-based systems has attracted extensive interest from both academic and industrial communities in recent years with the growing demand for voice-based applications. Prior works focus on independent research by the automatic speech recognition (ASR) and natural language processing (NLP) communities, or on jointly modeling the speech and NLP problems focusing on a single dataset or single NLP task. To facilitate the development of spoken language research, we introduce MTL-SLT, a multi-task learning framework for spoken language tasks. MTL-SLT takes speech as input, and outputs transcription, intent, named entities, summaries, and answers to text queries, supporting the tasks of spoken language understanding, spoken summarization and spoken question answering respectively. The proposed framework benefits from three key aspects: 1) pre-trained sub-networks of ASR model and language model; 2) multi-task learning objective to exploit shared knowledge from different tasks; 3) end-to-end training of ASR and downstream NLP task based on sequence loss. We obtain state-of-the-art results on spoken language understanding tasks such as SLURP and ATIS. Spoken summarization results are reported on a new dataset: Spoken-Gigaword.</abstract>
<identifier type="citekey">huang-etal-2022-mtl</identifier>
<identifier type="doi">10.18653/v1/2022.nlp4convai-1.11</identifier>
<location>
<url>https://aclanthology.org/2022.nlp4convai-1.11</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>120</start>
<end>130</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MTL-SLT: Multi-Task Learning for Spoken Language Tasks
%A Huang, Zhiqi
%A Rao, Milind
%A Raju, Anirudh
%A Zhang, Zhe
%A Bui, Bach
%A Lee, Chul
%Y Liu, Bing
%Y Papangelis, Alexandros
%Y Ultes, Stefan
%Y Rastogi, Abhinav
%Y Chen, Yun-Nung
%Y Spithourakis, Georgios
%Y Nouri, Elnaz
%Y Shi, Weiyan
%S Proceedings of the 4th Workshop on NLP for Conversational AI
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F huang-etal-2022-mtl
%X Language understanding in speech-based systems has attracted extensive interest from both academic and industrial communities in recent years with the growing demand for voice-based applications. Prior works focus on independent research by the automatic speech recognition (ASR) and natural language processing (NLP) communities, or on jointly modeling the speech and NLP problems focusing on a single dataset or single NLP task. To facilitate the development of spoken language research, we introduce MTL-SLT, a multi-task learning framework for spoken language tasks. MTL-SLT takes speech as input, and outputs transcription, intent, named entities, summaries, and answers to text queries, supporting the tasks of spoken language understanding, spoken summarization and spoken question answering respectively. The proposed framework benefits from three key aspects: 1) pre-trained sub-networks of ASR model and language model; 2) multi-task learning objective to exploit shared knowledge from different tasks; 3) end-to-end training of ASR and downstream NLP task based on sequence loss. We obtain state-of-the-art results on spoken language understanding tasks such as SLURP and ATIS. Spoken summarization results are reported on a new dataset: Spoken-Gigaword.
%R 10.18653/v1/2022.nlp4convai-1.11
%U https://aclanthology.org/2022.nlp4convai-1.11
%U https://doi.org/10.18653/v1/2022.nlp4convai-1.11
%P 120-130
Markdown (Informal)
[MTL-SLT: Multi-Task Learning for Spoken Language Tasks](https://aclanthology.org/2022.nlp4convai-1.11) (Huang et al., NLP4ConvAI 2022)
ACL
- Zhiqi Huang, Milind Rao, Anirudh Raju, Zhe Zhang, Bach Bui, and Chul Lee. 2022. MTL-SLT: Multi-Task Learning for Spoken Language Tasks. In Proceedings of the 4th Workshop on NLP for Conversational AI, pages 120–130, Dublin, Ireland. Association for Computational Linguistics.