@inproceedings{wicks-post-2021-unified,
title = "A unified approach to sentence segmentation of punctuated text in many languages",
author = "Wicks, Rachel and
Post, Matt",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.309",
doi = "10.18653/v1/2021.acl-long.309",
pages = "3995--4007",
abstract = "The sentence is a fundamental unit of text processing. Yet sentences in the wild are commonly encountered not in isolation, but unsegmented within larger paragraphs and documents. Therefore, the first step in many NLP pipelines is \textit{sentence segmentation}. Despite its importance, this step is the subject of relatively little research. There are no standard test sets or even methods for evaluation, leaving researchers and engineers without a clear footing for evaluating and selecting models for the task. Existing tools have relatively small language coverage, and efforts to extend them to other languages are often ad hoc. We introduce a modern context-based modeling approach that provides a solution to the problem of segmenting punctuated text in many languages, and show how it can be trained on noisily-annotated data. We also establish a new 23-language multilingual evaluation set. Our approach exceeds high baselines set by existing methods on prior English corpora (WSJ and Brown corpora), and also performs well on average on our new evaluation set. We release our tool, ersatz, as open source.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wicks-post-2021-unified">
<titleInfo>
<title>A unified approach to sentence segmentation of punctuated text in many languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Wicks</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Post</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The sentence is a fundamental unit of text processing. Yet sentences in the wild are commonly encountered not in isolation, but unsegmented within larger paragraphs and documents. Therefore, the first step in many NLP pipelines is sentence segmentation. Despite its importance, this step is the subject of relatively little research. There are no standard test sets or even methods for evaluation, leaving researchers and engineers without a clear footing for evaluating and selecting models for the task. Existing tools have relatively small language coverage, and efforts to extend them to other languages are often ad hoc. We introduce a modern context-based modeling approach that provides a solution to the problem of segmenting punctuated text in many languages, and show how it can be trained on noisily-annotated data. We also establish a new 23-language multilingual evaluation set. Our approach exceeds high baselines set by existing methods on prior English corpora (WSJ and Brown corpora), and also performs well on average on our new evaluation set. We release our tool, ersatz, as open source.</abstract>
<identifier type="citekey">wicks-post-2021-unified</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.309</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.309</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>3995</start>
<end>4007</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A unified approach to sentence segmentation of punctuated text in many languages
%A Wicks, Rachel
%A Post, Matt
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F wicks-post-2021-unified
%X The sentence is a fundamental unit of text processing. Yet sentences in the wild are commonly encountered not in isolation, but unsegmented within larger paragraphs and documents. Therefore, the first step in many NLP pipelines is sentence segmentation. Despite its importance, this step is the subject of relatively little research. There are no standard test sets or even methods for evaluation, leaving researchers and engineers without a clear footing for evaluating and selecting models for the task. Existing tools have relatively small language coverage, and efforts to extend them to other languages are often ad hoc. We introduce a modern context-based modeling approach that provides a solution to the problem of segmenting punctuated text in many languages, and show how it can be trained on noisily-annotated data. We also establish a new 23-language multilingual evaluation set. Our approach exceeds high baselines set by existing methods on prior English corpora (WSJ and Brown corpora), and also performs well on average on our new evaluation set. We release our tool, ersatz, as open source.
%R 10.18653/v1/2021.acl-long.309
%U https://aclanthology.org/2021.acl-long.309
%U https://doi.org/10.18653/v1/2021.acl-long.309
%P 3995-4007
Markdown (Informal)
[A unified approach to sentence segmentation of punctuated text in many languages](https://aclanthology.org/2021.acl-long.309) (Wicks & Post, ACL-IJCNLP 2021)
ACL