@inproceedings{mori-etal-2016-japanese,
title = "A {J}apanese Chess Commentary Corpus",
author = "Mori, Shinsuke and
Richardson, John and
Ushiku, Atsushi and
Sasada, Tetsuro and
Kameko, Hirotaka and
Tsuruoka, Yoshimasa",
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/L16-1225",
pages = "1415--1420",
abstract = "In recent years there has been a surge of interest in the natural language prosessing related to the real world, such as symbol grounding, language generation, and nonlinguistic data search by natural language queries. In order to concentrate on language ambiguities, we propose to use a well-defined {``}real world,{''} that is game states. We built a corpus consisting of pairs of sentences and a game state. The game we focus on is shogi (Japanese chess). We collected 742,286 commentary sentences in Japanese. They are spontaneously generated contrary to natural language annotations in many image datasets provided by human workers on Amazon Mechanical Turk. We defined domain specific named entities and we segmented 2,508 sentences into words manually and annotated each word with a named entity tag. We describe a detailed definition of named entities and show some statistics of our game commentary corpus. We also show the results of the experiments of word segmentation and named entity recognition. The accuracies are as high as those on general domain texts indicating that we are ready to tackle various new problems related to the real world.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mori-etal-2016-japanese">
<titleInfo>
<title>A Japanese Chess Commentary 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">John</namePart>
<namePart type="family">Richardson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Hirotaka</namePart>
<namePart type="family">Kameko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoshimasa</namePart>
<namePart type="family">Tsuruoka</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>In recent years there has been a surge of interest in the natural language prosessing related to the real world, such as symbol grounding, language generation, and nonlinguistic data search by natural language queries. In order to concentrate on language ambiguities, we propose to use a well-defined “real world,” that is game states. We built a corpus consisting of pairs of sentences and a game state. The game we focus on is shogi (Japanese chess). We collected 742,286 commentary sentences in Japanese. They are spontaneously generated contrary to natural language annotations in many image datasets provided by human workers on Amazon Mechanical Turk. We defined domain specific named entities and we segmented 2,508 sentences into words manually and annotated each word with a named entity tag. We describe a detailed definition of named entities and show some statistics of our game commentary corpus. We also show the results of the experiments of word segmentation and named entity recognition. The accuracies are as high as those on general domain texts indicating that we are ready to tackle various new problems related to the real world.</abstract>
<identifier type="citekey">mori-etal-2016-japanese</identifier>
<location>
<url>https://aclanthology.org/L16-1225</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1415</start>
<end>1420</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Japanese Chess Commentary Corpus
%A Mori, Shinsuke
%A Richardson, John
%A Ushiku, Atsushi
%A Sasada, Tetsuro
%A Kameko, Hirotaka
%A Tsuruoka, Yoshimasa
%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 mori-etal-2016-japanese
%X In recent years there has been a surge of interest in the natural language prosessing related to the real world, such as symbol grounding, language generation, and nonlinguistic data search by natural language queries. In order to concentrate on language ambiguities, we propose to use a well-defined “real world,” that is game states. We built a corpus consisting of pairs of sentences and a game state. The game we focus on is shogi (Japanese chess). We collected 742,286 commentary sentences in Japanese. They are spontaneously generated contrary to natural language annotations in many image datasets provided by human workers on Amazon Mechanical Turk. We defined domain specific named entities and we segmented 2,508 sentences into words manually and annotated each word with a named entity tag. We describe a detailed definition of named entities and show some statistics of our game commentary corpus. We also show the results of the experiments of word segmentation and named entity recognition. The accuracies are as high as those on general domain texts indicating that we are ready to tackle various new problems related to the real world.
%U https://aclanthology.org/L16-1225
%P 1415-1420
Markdown (Informal)
[A Japanese Chess Commentary Corpus](https://aclanthology.org/L16-1225) (Mori et al., LREC 2016)
ACL
- Shinsuke Mori, John Richardson, Atsushi Ushiku, Tetsuro Sasada, Hirotaka Kameko, and Yoshimasa Tsuruoka. 2016. A Japanese Chess Commentary Corpus. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 1415–1420, Portorož, Slovenia. European Language Resources Association (ELRA).