@inproceedings{ushiku-etal-2016-language,
title = "Language Resource Addition Strategies for Raw Text Parsing",
author = "Ushiku, Atsushi and
Sasada, Tetsuro and
Mori, Shinsuke",
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/L16-1105",
pages = "664--671",
abstract = "We focus on the improvement of accuracy of raw text parsing, from the viewpoint of language resource addition. In Japanese, the raw text parsing is divided into three steps: word segmentation, part-of-speech tagging, and dependency parsing. We investigate the contribution of language resource addition in each of three steps to the improvement in accuracy for two domain corpora. The experimental results show that this improvement depends on the target domain. For example, when we handle well-written texts of limited vocabulary, white paper, an effective language resource is a word-POS pair sequence corpus for the parsing accuracy. So we conclude that it is important to check out the characteristics of the target domain and to choose a suitable language resource addition strategy for the parsing accuracy improvement.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ushiku-etal-2016-language">
<titleInfo>
<title>Language Resource Addition Strategies for Raw Text Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atsushi</namePart>
<namePart type="family">Ushiku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tetsuro</namePart>
<namePart type="family">Sasada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shinsuke</namePart>
<namePart type="family">Mori</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>We focus on the improvement of accuracy of raw text parsing, from the viewpoint of language resource addition. In Japanese, the raw text parsing is divided into three steps: word segmentation, part-of-speech tagging, and dependency parsing. We investigate the contribution of language resource addition in each of three steps to the improvement in accuracy for two domain corpora. The experimental results show that this improvement depends on the target domain. For example, when we handle well-written texts of limited vocabulary, white paper, an effective language resource is a word-POS pair sequence corpus for the parsing accuracy. So we conclude that it is important to check out the characteristics of the target domain and to choose a suitable language resource addition strategy for the parsing accuracy improvement.</abstract>
<identifier type="citekey">ushiku-etal-2016-language</identifier>
<location>
<url>https://aclanthology.org/L16-1105</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>664</start>
<end>671</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Resource Addition Strategies for Raw Text Parsing
%A Ushiku, Atsushi
%A Sasada, Tetsuro
%A Mori, Shinsuke
%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 ushiku-etal-2016-language
%X We focus on the improvement of accuracy of raw text parsing, from the viewpoint of language resource addition. In Japanese, the raw text parsing is divided into three steps: word segmentation, part-of-speech tagging, and dependency parsing. We investigate the contribution of language resource addition in each of three steps to the improvement in accuracy for two domain corpora. The experimental results show that this improvement depends on the target domain. For example, when we handle well-written texts of limited vocabulary, white paper, an effective language resource is a word-POS pair sequence corpus for the parsing accuracy. So we conclude that it is important to check out the characteristics of the target domain and to choose a suitable language resource addition strategy for the parsing accuracy improvement.
%U https://aclanthology.org/L16-1105
%P 664-671
Markdown (Informal)
[Language Resource Addition Strategies for Raw Text Parsing](https://aclanthology.org/L16-1105) (Ushiku et al., LREC 2016)
ACL
- Atsushi Ushiku, Tetsuro Sasada, and Shinsuke Mori. 2016. Language Resource Addition Strategies for Raw Text Parsing. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 664–671, Portorož, Slovenia. European Language Resources Association (ELRA).