@inproceedings{recski-etal-2010-np,
title = "{NP} Alignment in Bilingual Corpora",
author = "Recski, G{\'a}bor and
Rung, Andr{\'a}s and
Zs{\'e}der, Attila and
Kornai, Andr{\'a}s",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/531_Paper.pdf",
abstract = "Aligning the NPs of parallel corpora is logically halfway between the sentence- and word-alignment tasks that occupy much of the MT literature, but has received far less attention. NP alignment is a challenging problem, capable of rapidly exposing flaws both in the word-alignment and in the NP chunking algorithms one may bring to bear. It is also a very rewarding problem in that NPs are semantically natural translation units, which means that (i) word alignments will cross NP boundaries only exceptionally, and (ii) within sentences already aligned, the proportion of 1-1 alignments will be higher for NPs than words. We created a simple gold standard for English-Hungarian, Orwells 1984, (since this already exists in manually verified POS-tagged format in many languages thanks to the Multex and MultexEast project) by manually verifying the automaticaly generated NP chunking (we used the yamcha, mallet and hunchunk taggers) and manually aligning the maximal NPs and PPs. The maximum NP chunking problem is much harder than base NP chunking, with F-measure in the .7 range (as opposed to over .94 for base NPs). Since the results are highly impacted by the quality of the NP chunking, we tested our alignment algorithms both with real world (machine obtained) chunkings, where results are in the .35 range for the baseline algorithm which propagates GIZA++ word alignments to the NP level, and on idealized (manually obtained) chunkings, where the baseline reaches .4 and our current system reaches .64.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="recski-etal-2010-np">
<titleInfo>
<title>NP Alignment in Bilingual Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gábor</namePart>
<namePart type="family">Recski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">András</namePart>
<namePart type="family">Rung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Attila</namePart>
<namePart type="family">Zséder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">András</namePart>
<namePart type="family">Kornai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Aligning the NPs of parallel corpora is logically halfway between the sentence- and word-alignment tasks that occupy much of the MT literature, but has received far less attention. NP alignment is a challenging problem, capable of rapidly exposing flaws both in the word-alignment and in the NP chunking algorithms one may bring to bear. It is also a very rewarding problem in that NPs are semantically natural translation units, which means that (i) word alignments will cross NP boundaries only exceptionally, and (ii) within sentences already aligned, the proportion of 1-1 alignments will be higher for NPs than words. We created a simple gold standard for English-Hungarian, Orwells 1984, (since this already exists in manually verified POS-tagged format in many languages thanks to the Multex and MultexEast project) by manually verifying the automaticaly generated NP chunking (we used the yamcha, mallet and hunchunk taggers) and manually aligning the maximal NPs and PPs. The maximum NP chunking problem is much harder than base NP chunking, with F-measure in the .7 range (as opposed to over .94 for base NPs). Since the results are highly impacted by the quality of the NP chunking, we tested our alignment algorithms both with real world (machine obtained) chunkings, where results are in the .35 range for the baseline algorithm which propagates GIZA++ word alignments to the NP level, and on idealized (manually obtained) chunkings, where the baseline reaches .4 and our current system reaches .64.</abstract>
<identifier type="citekey">recski-etal-2010-np</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/531_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NP Alignment in Bilingual Corpora
%A Recski, Gábor
%A Rung, András
%A Zséder, Attila
%A Kornai, András
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F recski-etal-2010-np
%X Aligning the NPs of parallel corpora is logically halfway between the sentence- and word-alignment tasks that occupy much of the MT literature, but has received far less attention. NP alignment is a challenging problem, capable of rapidly exposing flaws both in the word-alignment and in the NP chunking algorithms one may bring to bear. It is also a very rewarding problem in that NPs are semantically natural translation units, which means that (i) word alignments will cross NP boundaries only exceptionally, and (ii) within sentences already aligned, the proportion of 1-1 alignments will be higher for NPs than words. We created a simple gold standard for English-Hungarian, Orwells 1984, (since this already exists in manually verified POS-tagged format in many languages thanks to the Multex and MultexEast project) by manually verifying the automaticaly generated NP chunking (we used the yamcha, mallet and hunchunk taggers) and manually aligning the maximal NPs and PPs. The maximum NP chunking problem is much harder than base NP chunking, with F-measure in the .7 range (as opposed to over .94 for base NPs). Since the results are highly impacted by the quality of the NP chunking, we tested our alignment algorithms both with real world (machine obtained) chunkings, where results are in the .35 range for the baseline algorithm which propagates GIZA++ word alignments to the NP level, and on idealized (manually obtained) chunkings, where the baseline reaches .4 and our current system reaches .64.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/531_Paper.pdf
Markdown (Informal)
[NP Alignment in Bilingual Corpora](http://www.lrec-conf.org/proceedings/lrec2010/pdf/531_Paper.pdf) (Recski et al., LREC 2010)
ACL
- Gábor Recski, András Rung, Attila Zséder, and András Kornai. 2010. NP Alignment in Bilingual Corpora. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).