@inproceedings{paun-2021-parallel,
title = "Parallel Text Alignment and Monolingual Parallel Corpus Creation from Philosophical Texts for Text Simplification",
author = "Paun, Stefan",
editor = "Durmus, Esin and
Gupta, Vivek and
Liu, Nelson and
Peng, Nanyun and
Su, Yu",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-srw.6",
doi = "10.18653/v1/2021.naacl-srw.6",
pages = "40--46",
abstract = "Text simplification is a growing field with many potential useful applications. Training text simplification algorithms generally requires a lot of annotated data, however there are not many corpora suitable for this task. We propose a new unsupervised method for aligning text based on Doc2Vec embeddings and a new alignment algorithm, capable of aligning texts at different levels. Initial evaluation shows promising results for the new approach. We used the newly developed approach to create a new monolingual parallel corpus composed of the works of English early modern philosophers and their corresponding simplified versions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="paun-2021-parallel">
<titleInfo>
<title>Parallel Text Alignment and Monolingual Parallel Corpus Creation from Philosophical Texts for Text Simplification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Paun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Esin</namePart>
<namePart type="family">Durmus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nelson</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Su</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>Text simplification is a growing field with many potential useful applications. Training text simplification algorithms generally requires a lot of annotated data, however there are not many corpora suitable for this task. We propose a new unsupervised method for aligning text based on Doc2Vec embeddings and a new alignment algorithm, capable of aligning texts at different levels. Initial evaluation shows promising results for the new approach. We used the newly developed approach to create a new monolingual parallel corpus composed of the works of English early modern philosophers and their corresponding simplified versions.</abstract>
<identifier type="citekey">paun-2021-parallel</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-srw.6</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-srw.6</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>40</start>
<end>46</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parallel Text Alignment and Monolingual Parallel Corpus Creation from Philosophical Texts for Text Simplification
%A Paun, Stefan
%Y Durmus, Esin
%Y Gupta, Vivek
%Y Liu, Nelson
%Y Peng, Nanyun
%Y Su, Yu
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F paun-2021-parallel
%X Text simplification is a growing field with many potential useful applications. Training text simplification algorithms generally requires a lot of annotated data, however there are not many corpora suitable for this task. We propose a new unsupervised method for aligning text based on Doc2Vec embeddings and a new alignment algorithm, capable of aligning texts at different levels. Initial evaluation shows promising results for the new approach. We used the newly developed approach to create a new monolingual parallel corpus composed of the works of English early modern philosophers and their corresponding simplified versions.
%R 10.18653/v1/2021.naacl-srw.6
%U https://aclanthology.org/2021.naacl-srw.6
%U https://doi.org/10.18653/v1/2021.naacl-srw.6
%P 40-46
Markdown (Informal)
[Parallel Text Alignment and Monolingual Parallel Corpus Creation from Philosophical Texts for Text Simplification](https://aclanthology.org/2021.naacl-srw.6) (Paun, NAACL 2021)
ACL