@inproceedings{mori-neubig-2014-language,
title = "Language Resource Addition: Dictionary or Corpus?",
author = "Mori, Shinsuke and
Neubig, Graham",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/648_Paper.pdf",
pages = "1631--1636",
abstract = "In this paper, we investigate the relative effect of two strategies of language resource additions to the word segmentation problem and part-of-speech tagging problem in Japanese. The first strategy is adding entries to the dictionary and the second is adding annotated sentences to the training corpus. The experimental results showed that the annotated sentence addition to the training corpus is better than the entries addition to the dictionary. And the annotated sentence addition is efficient especially when we add new words with contexts of three real occurrences as partially annotated sentences. According to this knowledge, we executed annotation on the invention disclosure texts and observed word segmentation accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mori-neubig-2014-language">
<titleInfo>
<title>Language Resource Addition: Dictionary or Corpus?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shinsuke</namePart>
<namePart type="family">Mori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we investigate the relative effect of two strategies of language resource additions to the word segmentation problem and part-of-speech tagging problem in Japanese. The first strategy is adding entries to the dictionary and the second is adding annotated sentences to the training corpus. The experimental results showed that the annotated sentence addition to the training corpus is better than the entries addition to the dictionary. And the annotated sentence addition is efficient especially when we add new words with contexts of three real occurrences as partially annotated sentences. According to this knowledge, we executed annotation on the invention disclosure texts and observed word segmentation accuracy.</abstract>
<identifier type="citekey">mori-neubig-2014-language</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/648_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1631</start>
<end>1636</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Resource Addition: Dictionary or Corpus?
%A Mori, Shinsuke
%A Neubig, Graham
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F mori-neubig-2014-language
%X In this paper, we investigate the relative effect of two strategies of language resource additions to the word segmentation problem and part-of-speech tagging problem in Japanese. The first strategy is adding entries to the dictionary and the second is adding annotated sentences to the training corpus. The experimental results showed that the annotated sentence addition to the training corpus is better than the entries addition to the dictionary. And the annotated sentence addition is efficient especially when we add new words with contexts of three real occurrences as partially annotated sentences. According to this knowledge, we executed annotation on the invention disclosure texts and observed word segmentation accuracy.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/648_Paper.pdf
%P 1631-1636
Markdown (Informal)
[Language Resource Addition: Dictionary or Corpus?](http://www.lrec-conf.org/proceedings/lrec2014/pdf/648_Paper.pdf) (Mori & Neubig, LREC 2014)
ACL
- Shinsuke Mori and Graham Neubig. 2014. Language Resource Addition: Dictionary or Corpus?. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 1631–1636, Reykjavik, Iceland. European Language Resources Association (ELRA).