@inproceedings{xu-yvon-2016-novel,
title = "Novel elicitation and annotation schemes for sentential and sub-sentential alignments of bitexts",
author = "Xu, Yong and
Yvon, Fran{\c{c}}ois",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1099",
pages = "628--635",
abstract = "Resources for evaluating sentence-level and word-level alignment algorithms are unsatisfactory. Regarding sentence alignments, the existing data is too scarce, especially when it comes to difficult bitexts, containing instances of non-literal translations. Regarding word-level alignments, most available hand-aligned data provide a complete annotation at the level of words that is difficult to exploit, for lack of a clear semantics for alignment links. In this study, we propose new methodologies for collecting human judgements on alignment links, which have been used to annotate 4 new data sets, at the sentence and at the word level. These will be released online, with the hope that they will prove useful to evaluate alignment software and quality estimation tools for automatic alignment. Keywords: Parallel corpora, Sentence Alignments, Word Alignments, Confidence Estimation",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-yvon-2016-novel">
<titleInfo>
<title>Novel elicitation and annotation schemes for sentential and sub-sentential alignments of bitexts</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">François</namePart>
<namePart type="family">Yvon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Resources for evaluating sentence-level and word-level alignment algorithms are unsatisfactory. Regarding sentence alignments, the existing data is too scarce, especially when it comes to difficult bitexts, containing instances of non-literal translations. Regarding word-level alignments, most available hand-aligned data provide a complete annotation at the level of words that is difficult to exploit, for lack of a clear semantics for alignment links. In this study, we propose new methodologies for collecting human judgements on alignment links, which have been used to annotate 4 new data sets, at the sentence and at the word level. These will be released online, with the hope that they will prove useful to evaluate alignment software and quality estimation tools for automatic alignment. Keywords: Parallel corpora, Sentence Alignments, Word Alignments, Confidence Estimation</abstract>
<identifier type="citekey">xu-yvon-2016-novel</identifier>
<location>
<url>https://aclanthology.org/L16-1099</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>628</start>
<end>635</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Novel elicitation and annotation schemes for sentential and sub-sentential alignments of bitexts
%A Xu, Yong
%A Yvon, François
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F xu-yvon-2016-novel
%X Resources for evaluating sentence-level and word-level alignment algorithms are unsatisfactory. Regarding sentence alignments, the existing data is too scarce, especially when it comes to difficult bitexts, containing instances of non-literal translations. Regarding word-level alignments, most available hand-aligned data provide a complete annotation at the level of words that is difficult to exploit, for lack of a clear semantics for alignment links. In this study, we propose new methodologies for collecting human judgements on alignment links, which have been used to annotate 4 new data sets, at the sentence and at the word level. These will be released online, with the hope that they will prove useful to evaluate alignment software and quality estimation tools for automatic alignment. Keywords: Parallel corpora, Sentence Alignments, Word Alignments, Confidence Estimation
%U https://aclanthology.org/L16-1099
%P 628-635
Markdown (Informal)
[Novel elicitation and annotation schemes for sentential and sub-sentential alignments of bitexts](https://aclanthology.org/L16-1099) (Xu & Yvon, LREC 2016)
ACL