@inproceedings{alam-etal-2020-punctuation,
title = "Punctuation Restoration using Transformer Models for High-and Low-Resource Languages",
author = "Alam, Tanvirul and
Khan, Akib and
Alam, Firoj",
booktitle = "Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wnut-1.18",
doi = "10.18653/v1/2020.wnut-1.18",
pages = "132--142",
abstract = "Punctuation restoration is a common post-processing problem for Automatic Speech Recognition (ASR) systems. It is important to improve the readability of the transcribed text for the human reader and facilitate NLP tasks. Current state-of-art address this problem using different deep learning models. Recently, transformer models have proven their success in downstream NLP tasks, and these models have been explored very little for the punctuation restoration problem. In this work, we explore different transformer based models and propose an augmentation strategy for this task, focusing on high-resource (English) and low-resource (Bangla) languages. For English, we obtain comparable state-of-the-art results, while for Bangla, it is the first reported work, which can serve as a strong baseline for future work. We have made our developed Bangla dataset publicly available for the research community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alam-etal-2020-punctuation">
<titleInfo>
<title>Punctuation Restoration using Transformer Models for High-and Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tanvirul</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akib</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Punctuation restoration is a common post-processing problem for Automatic Speech Recognition (ASR) systems. It is important to improve the readability of the transcribed text for the human reader and facilitate NLP tasks. Current state-of-art address this problem using different deep learning models. Recently, transformer models have proven their success in downstream NLP tasks, and these models have been explored very little for the punctuation restoration problem. In this work, we explore different transformer based models and propose an augmentation strategy for this task, focusing on high-resource (English) and low-resource (Bangla) languages. For English, we obtain comparable state-of-the-art results, while for Bangla, it is the first reported work, which can serve as a strong baseline for future work. We have made our developed Bangla dataset publicly available for the research community.</abstract>
<identifier type="citekey">alam-etal-2020-punctuation</identifier>
<identifier type="doi">10.18653/v1/2020.wnut-1.18</identifier>
<location>
<url>https://aclanthology.org/2020.wnut-1.18</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>132</start>
<end>142</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Punctuation Restoration using Transformer Models for High-and Low-Resource Languages
%A Alam, Tanvirul
%A Khan, Akib
%A Alam, Firoj
%S Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F alam-etal-2020-punctuation
%X Punctuation restoration is a common post-processing problem for Automatic Speech Recognition (ASR) systems. It is important to improve the readability of the transcribed text for the human reader and facilitate NLP tasks. Current state-of-art address this problem using different deep learning models. Recently, transformer models have proven their success in downstream NLP tasks, and these models have been explored very little for the punctuation restoration problem. In this work, we explore different transformer based models and propose an augmentation strategy for this task, focusing on high-resource (English) and low-resource (Bangla) languages. For English, we obtain comparable state-of-the-art results, while for Bangla, it is the first reported work, which can serve as a strong baseline for future work. We have made our developed Bangla dataset publicly available for the research community.
%R 10.18653/v1/2020.wnut-1.18
%U https://aclanthology.org/2020.wnut-1.18
%U https://doi.org/10.18653/v1/2020.wnut-1.18
%P 132-142
Markdown (Informal)
[Punctuation Restoration using Transformer Models for High-and Low-Resource Languages](https://aclanthology.org/2020.wnut-1.18) (Alam et al., WNUT 2020)
ACL