@inproceedings{tanaka-etal-2020-constructing,
title = "Constructing a Public Meeting Corpus",
author = "Tanaka, Koji and
Chu, Chenhui and
Ren, Haolin and
Renoust, Benjamin and
Nakashima, Yuta and
Takemura, Noriko and
Nagahara, Hajime and
Fujikawa, Takao",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.238",
pages = "1934--1940",
abstract = "In this paper, we propose a full pipeline of analysis of a large corpus about a century of public meeting in historical Australian news papers, from construction to visual exploration. The corpus construction method is based on image processing and OCR. We digitize and transcribe texts of the specific topic of public meeting. Experiments show that our proposed method achieves a F-score of 87.8{\%} for corpus construction. As a result, we built a content search tool for temporal and semantic content analysis.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tanaka-etal-2020-constructing">
<titleInfo>
<title>Constructing a Public Meeting Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Koji</namePart>
<namePart type="family">Tanaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenhui</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haolin</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Renoust</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuta</namePart>
<namePart type="family">Nakashima</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noriko</namePart>
<namePart type="family">Takemura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hajime</namePart>
<namePart type="family">Nagahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takao</namePart>
<namePart type="family">Fujikawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>In this paper, we propose a full pipeline of analysis of a large corpus about a century of public meeting in historical Australian news papers, from construction to visual exploration. The corpus construction method is based on image processing and OCR. We digitize and transcribe texts of the specific topic of public meeting. Experiments show that our proposed method achieves a F-score of 87.8% for corpus construction. As a result, we built a content search tool for temporal and semantic content analysis.</abstract>
<identifier type="citekey">tanaka-etal-2020-constructing</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.238</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>1934</start>
<end>1940</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Constructing a Public Meeting Corpus
%A Tanaka, Koji
%A Chu, Chenhui
%A Ren, Haolin
%A Renoust, Benjamin
%A Nakashima, Yuta
%A Takemura, Noriko
%A Nagahara, Hajime
%A Fujikawa, Takao
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F tanaka-etal-2020-constructing
%X In this paper, we propose a full pipeline of analysis of a large corpus about a century of public meeting in historical Australian news papers, from construction to visual exploration. The corpus construction method is based on image processing and OCR. We digitize and transcribe texts of the specific topic of public meeting. Experiments show that our proposed method achieves a F-score of 87.8% for corpus construction. As a result, we built a content search tool for temporal and semantic content analysis.
%U https://aclanthology.org/2020.lrec-1.238
%P 1934-1940
Markdown (Informal)
[Constructing a Public Meeting Corpus](https://aclanthology.org/2020.lrec-1.238) (Tanaka et al., LREC 2020)
ACL
- Koji Tanaka, Chenhui Chu, Haolin Ren, Benjamin Renoust, Yuta Nakashima, Noriko Takemura, Hajime Nagahara, and Takao Fujikawa. 2020. Constructing a Public Meeting Corpus. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 1934–1940, Marseille, France. European Language Resources Association.