@inproceedings{pogoda-walkowiak-2021-comprehensive-punctuation,
title = "Comprehensive Punctuation Restoration for {E}nglish and {P}olish",
author = "Pogoda, Micha{\l} and
Walkowiak, Tomasz",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.393",
doi = "10.18653/v1/2021.findings-emnlp.393",
pages = "4610--4619",
abstract = "Punctuation restoration is a fundamental requirement for the readability of text derived from Automatic Speech Recognition (ASR) systems. Most contemporary solutions are limited to predicting only a few of the most frequently occurring marks, such as periods, commas, and question marks - and only one per word. However, in written language, we deal with a much larger number of punctuation characters (such as parentheses, hyphens, etc.), and their combinations (like parenthesis followed by a dot). Such comprehensive punctuation cannot always be unambiguously reduced to a basic set of the most frequently occurring marks. In this work, we evaluate several methods in the comprehensive punctuation reconstruction task. We conduct experiments on parallel corpora of two different languages, English and Polish - languages with a relatively simple and complex morphology, respectively. We also investigate the influence of building a model on comprehensive punctuation on the quality of the basic punctuation restoration task",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pogoda-walkowiak-2021-comprehensive-punctuation">
<titleInfo>
<title>Comprehensive Punctuation Restoration for English and Polish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="family">Pogoda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomasz</namePart>
<namePart type="family">Walkowiak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Punctuation restoration is a fundamental requirement for the readability of text derived from Automatic Speech Recognition (ASR) systems. Most contemporary solutions are limited to predicting only a few of the most frequently occurring marks, such as periods, commas, and question marks - and only one per word. However, in written language, we deal with a much larger number of punctuation characters (such as parentheses, hyphens, etc.), and their combinations (like parenthesis followed by a dot). Such comprehensive punctuation cannot always be unambiguously reduced to a basic set of the most frequently occurring marks. In this work, we evaluate several methods in the comprehensive punctuation reconstruction task. We conduct experiments on parallel corpora of two different languages, English and Polish - languages with a relatively simple and complex morphology, respectively. We also investigate the influence of building a model on comprehensive punctuation on the quality of the basic punctuation restoration task</abstract>
<identifier type="citekey">pogoda-walkowiak-2021-comprehensive-punctuation</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.393</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.393</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>4610</start>
<end>4619</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comprehensive Punctuation Restoration for English and Polish
%A Pogoda, Michał
%A Walkowiak, Tomasz
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F pogoda-walkowiak-2021-comprehensive-punctuation
%X Punctuation restoration is a fundamental requirement for the readability of text derived from Automatic Speech Recognition (ASR) systems. Most contemporary solutions are limited to predicting only a few of the most frequently occurring marks, such as periods, commas, and question marks - and only one per word. However, in written language, we deal with a much larger number of punctuation characters (such as parentheses, hyphens, etc.), and their combinations (like parenthesis followed by a dot). Such comprehensive punctuation cannot always be unambiguously reduced to a basic set of the most frequently occurring marks. In this work, we evaluate several methods in the comprehensive punctuation reconstruction task. We conduct experiments on parallel corpora of two different languages, English and Polish - languages with a relatively simple and complex morphology, respectively. We also investigate the influence of building a model on comprehensive punctuation on the quality of the basic punctuation restoration task
%R 10.18653/v1/2021.findings-emnlp.393
%U https://aclanthology.org/2021.findings-emnlp.393
%U https://doi.org/10.18653/v1/2021.findings-emnlp.393
%P 4610-4619
Markdown (Informal)
[Comprehensive Punctuation Restoration for English and Polish](https://aclanthology.org/2021.findings-emnlp.393) (Pogoda & Walkowiak, Findings 2021)
ACL