@inproceedings{suzuki-etal-2016-correcting,
title = "Correcting Errors in a Treebank Based on Tree Mining",
author = "Suzuki, Kanta and
Kato, Yoshihide and
Matsubara, Shigeki",
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/L16-1244",
pages = "1540--1545",
abstract = "This paper provides a new method to correct annotation errors in a treebank. The previous error correction method constructs a pseudo parallel corpus where incorrect partial parse trees are paired with correct ones, and extracts error correction rules from the parallel corpus. By applying these rules to a treebank, the method corrects errors. However, this method does not achieve wide coverage of error correction. To achieve wide coverage, our method adopts a different approach. In our method, we consider that an infrequent pattern which can be transformed to a frequent one is an annotation error pattern. Based on a tree mining technique, our method seeks such infrequent tree patterns, and constructs error correction rules each of which consists of an infrequent pattern and a corresponding frequent pattern. We conducted an experiment using the Penn Treebank. We obtained 1,987 rules which are not constructed by the previous method, and the rules achieved good precision.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="suzuki-etal-2016-correcting">
<titleInfo>
<title>Correcting Errors in a Treebank Based on Tree Mining</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kanta</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoshihide</namePart>
<namePart type="family">Kato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shigeki</namePart>
<namePart type="family">Matsubara</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>
<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>This paper provides a new method to correct annotation errors in a treebank. The previous error correction method constructs a pseudo parallel corpus where incorrect partial parse trees are paired with correct ones, and extracts error correction rules from the parallel corpus. By applying these rules to a treebank, the method corrects errors. However, this method does not achieve wide coverage of error correction. To achieve wide coverage, our method adopts a different approach. In our method, we consider that an infrequent pattern which can be transformed to a frequent one is an annotation error pattern. Based on a tree mining technique, our method seeks such infrequent tree patterns, and constructs error correction rules each of which consists of an infrequent pattern and a corresponding frequent pattern. We conducted an experiment using the Penn Treebank. We obtained 1,987 rules which are not constructed by the previous method, and the rules achieved good precision.</abstract>
<identifier type="citekey">suzuki-etal-2016-correcting</identifier>
<location>
<url>https://aclanthology.org/L16-1244</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1540</start>
<end>1545</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Correcting Errors in a Treebank Based on Tree Mining
%A Suzuki, Kanta
%A Kato, Yoshihide
%A Matsubara, Shigeki
%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 suzuki-etal-2016-correcting
%X This paper provides a new method to correct annotation errors in a treebank. The previous error correction method constructs a pseudo parallel corpus where incorrect partial parse trees are paired with correct ones, and extracts error correction rules from the parallel corpus. By applying these rules to a treebank, the method corrects errors. However, this method does not achieve wide coverage of error correction. To achieve wide coverage, our method adopts a different approach. In our method, we consider that an infrequent pattern which can be transformed to a frequent one is an annotation error pattern. Based on a tree mining technique, our method seeks such infrequent tree patterns, and constructs error correction rules each of which consists of an infrequent pattern and a corresponding frequent pattern. We conducted an experiment using the Penn Treebank. We obtained 1,987 rules which are not constructed by the previous method, and the rules achieved good precision.
%U https://aclanthology.org/L16-1244
%P 1540-1545
Markdown (Informal)
[Correcting Errors in a Treebank Based on Tree Mining](https://aclanthology.org/L16-1244) (Suzuki et al., LREC 2016)
ACL
- Kanta Suzuki, Yoshihide Kato, and Shigeki Matsubara. 2016. Correcting Errors in a Treebank Based on Tree Mining. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 1540–1545, Portorož, Slovenia. European Language Resources Association (ELRA).