@inproceedings{xu-etal-2015-sentence,
title = "Sentence alignment for literary texts: The state-of-the-art and beyond",
author = "Xu, Yong and
Max, Aur{\'e}lien and
Yvon, Fran{\c{c}}ois",
booktitle = "Linguistic Issues in Language Technology, Volume 12, 2015 - Literature Lifts up Computational Linguistics",
month = oct,
year = "2015",
publisher = "CSLI Publications",
url = "https://aclanthology.org/2015.lilt-12.6",
abstract = "Literary works are becoming increasingly available in electronic formats, thus quickly transforming editorial processes and reading habits. In the context of the global enthusiasm for multilingualism, the rapid spread of e-book readers, such as Amazon Kindle R or Kobo Touch R , fosters the development of a new generation of reading tools for bilingual books. In particular, literary works, when available in several languages, offer an attractive perspective for self-development or everyday leisure reading, but also for activities such as language learning, translation or literary studies. An important issue in the automatic processing of multilingual e-books is the alignment between textual units. Alignment could help identify corresponding text units in different languages, which would be particularly beneficial to bilingual readers and translation professionals. Computing automatic alignments for literary works, however, is a task more challenging than in the case of better behaved corpora such as parliamentary proceedings or technical manuals. In this paper, we revisit the problem of computing high-quality. alignment for literary works. We first perform a large-scale evaluation of automatic alignment for literary texts, which provides a fair assessment of the actual difficulty of this task. We then introduce a two-pass approach, based on a maximum entropy model. Experimental results for novels available in English and French or in English and Spanish demonstrate the effectiveness of our method.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2015-sentence">
<titleInfo>
<title>Sentence alignment for literary texts: The state-of-the-art and beyond</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurélien</namePart>
<namePart type="family">Max</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Yvon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2015-oct</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Linguistic Issues in Language Technology, Volume 12, 2015 - Literature Lifts up Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>CSLI Publications</publisher>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Literary works are becoming increasingly available in electronic formats, thus quickly transforming editorial processes and reading habits. In the context of the global enthusiasm for multilingualism, the rapid spread of e-book readers, such as Amazon Kindle R or Kobo Touch R , fosters the development of a new generation of reading tools for bilingual books. In particular, literary works, when available in several languages, offer an attractive perspective for self-development or everyday leisure reading, but also for activities such as language learning, translation or literary studies. An important issue in the automatic processing of multilingual e-books is the alignment between textual units. Alignment could help identify corresponding text units in different languages, which would be particularly beneficial to bilingual readers and translation professionals. Computing automatic alignments for literary works, however, is a task more challenging than in the case of better behaved corpora such as parliamentary proceedings or technical manuals. In this paper, we revisit the problem of computing high-quality. alignment for literary works. We first perform a large-scale evaluation of automatic alignment for literary texts, which provides a fair assessment of the actual difficulty of this task. We then introduce a two-pass approach, based on a maximum entropy model. Experimental results for novels available in English and French or in English and Spanish demonstrate the effectiveness of our method.</abstract>
<identifier type="citekey">xu-etal-2015-sentence</identifier>
<location>
<url>https://aclanthology.org/2015.lilt-12.6</url>
</location>
<part>
<date>2015-oct</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sentence alignment for literary texts: The state-of-the-art and beyond
%A Xu, Yong
%A Max, Aurélien
%A Yvon, François
%S Linguistic Issues in Language Technology, Volume 12, 2015 - Literature Lifts up Computational Linguistics
%D 2015
%8 oct
%I CSLI Publications
%F xu-etal-2015-sentence
%X Literary works are becoming increasingly available in electronic formats, thus quickly transforming editorial processes and reading habits. In the context of the global enthusiasm for multilingualism, the rapid spread of e-book readers, such as Amazon Kindle R or Kobo Touch R , fosters the development of a new generation of reading tools for bilingual books. In particular, literary works, when available in several languages, offer an attractive perspective for self-development or everyday leisure reading, but also for activities such as language learning, translation or literary studies. An important issue in the automatic processing of multilingual e-books is the alignment between textual units. Alignment could help identify corresponding text units in different languages, which would be particularly beneficial to bilingual readers and translation professionals. Computing automatic alignments for literary works, however, is a task more challenging than in the case of better behaved corpora such as parliamentary proceedings or technical manuals. In this paper, we revisit the problem of computing high-quality. alignment for literary works. We first perform a large-scale evaluation of automatic alignment for literary texts, which provides a fair assessment of the actual difficulty of this task. We then introduce a two-pass approach, based on a maximum entropy model. Experimental results for novels available in English and French or in English and Spanish demonstrate the effectiveness of our method.
%U https://aclanthology.org/2015.lilt-12.6
Markdown (Informal)
[Sentence alignment for literary texts: The state-of-the-art and beyond](https://aclanthology.org/2015.lilt-12.6) (Xu et al., LILT 2015)
ACL