@inproceedings{zhu-etal-2022-punctuation,
title = "Punctuation Restoration in {S}panish Customer Support Transcripts using Transfer Learning",
author = "Zhu, Xiliang and
Gardiner, Shayna and
Rossouw, David and
Rold{\'a}n, Tere and
Corston-Oliver, Simon",
editor = "Cherry, Colin and
Fan, Angela and
Foster, George and
Haffari, Gholamreza (Reza) and
Khadivi, Shahram and
Peng, Nanyun (Violet) and
Ren, Xiang and
Shareghi, Ehsan and
Swayamdipta, Swabha",
booktitle = "Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing",
month = jul,
year = "2022",
address = "Hybrid",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.deeplo-1.9",
doi = "10.18653/v1/2022.deeplo-1.9",
pages = "80--89",
abstract = "Automatic Speech Recognition (ASR) systems typically produce unpunctuated transcripts that have poor readability. In addition, building a punctuation restoration system is challenging for low-resource languages, especially for domain-specific applications. In this paper, we propose a Spanish punctuation restoration system designed for a real-time customer support transcription service. To address the data sparsity of Spanish transcripts in the customer support domain, we introduce two transferlearning-based strategies: 1) domain adaptation using out-of-domain Spanish text data; 2) crosslingual transfer learning leveraging in-domain English transcript data. Our experiment results show that these strategies improve the accuracy of the Spanish punctuation restoration system.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2022-punctuation">
<titleInfo>
<title>Punctuation Restoration in Spanish Customer Support Transcripts using Transfer Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiliang</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shayna</namePart>
<namePart type="family">Gardiner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Rossouw</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tere</namePart>
<namePart type="family">Roldán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Corston-Oliver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Cherry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="given">(Reza)</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahram</namePart>
<namePart type="family">Khadivi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="given">(Violet)</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Shareghi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic Speech Recognition (ASR) systems typically produce unpunctuated transcripts that have poor readability. In addition, building a punctuation restoration system is challenging for low-resource languages, especially for domain-specific applications. In this paper, we propose a Spanish punctuation restoration system designed for a real-time customer support transcription service. To address the data sparsity of Spanish transcripts in the customer support domain, we introduce two transferlearning-based strategies: 1) domain adaptation using out-of-domain Spanish text data; 2) crosslingual transfer learning leveraging in-domain English transcript data. Our experiment results show that these strategies improve the accuracy of the Spanish punctuation restoration system.</abstract>
<identifier type="citekey">zhu-etal-2022-punctuation</identifier>
<identifier type="doi">10.18653/v1/2022.deeplo-1.9</identifier>
<location>
<url>https://aclanthology.org/2022.deeplo-1.9</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>80</start>
<end>89</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Punctuation Restoration in Spanish Customer Support Transcripts using Transfer Learning
%A Zhu, Xiliang
%A Gardiner, Shayna
%A Rossouw, David
%A Roldán, Tere
%A Corston-Oliver, Simon
%Y Cherry, Colin
%Y Fan, Angela
%Y Foster, George
%Y Haffari, Gholamreza (Reza)
%Y Khadivi, Shahram
%Y Peng, Nanyun (Violet)
%Y Ren, Xiang
%Y Shareghi, Ehsan
%Y Swayamdipta, Swabha
%S Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing
%D 2022
%8 July
%I Association for Computational Linguistics
%C Hybrid
%F zhu-etal-2022-punctuation
%X Automatic Speech Recognition (ASR) systems typically produce unpunctuated transcripts that have poor readability. In addition, building a punctuation restoration system is challenging for low-resource languages, especially for domain-specific applications. In this paper, we propose a Spanish punctuation restoration system designed for a real-time customer support transcription service. To address the data sparsity of Spanish transcripts in the customer support domain, we introduce two transferlearning-based strategies: 1) domain adaptation using out-of-domain Spanish text data; 2) crosslingual transfer learning leveraging in-domain English transcript data. Our experiment results show that these strategies improve the accuracy of the Spanish punctuation restoration system.
%R 10.18653/v1/2022.deeplo-1.9
%U https://aclanthology.org/2022.deeplo-1.9
%U https://doi.org/10.18653/v1/2022.deeplo-1.9
%P 80-89
Markdown (Informal)
[Punctuation Restoration in Spanish Customer Support Transcripts using Transfer Learning](https://aclanthology.org/2022.deeplo-1.9) (Zhu et al., DeepLo 2022)
ACL