@inproceedings{doi-etal-2020-tddc,
title = "{TDDC}: Timely Disclosure Documents Corpus",
author = "Doi, Nobushige and
Oda, Yusuke and
Nakazawa, Toshiaki",
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-1.459",
pages = "3719--3726",
abstract = "In this paper, we describe the details of the Timely Disclosure Documents Corpus (TDDC). TDDC was prepared by manually aligning the sentences from past Japanese and English timely disclosure documents in PDF format published by companies listed on the Tokyo Stock Exchange. TDDC consists of approximately 1.4 million parallel sentences in Japanese and English. TDDC was used as the official dataset for the 6th Workshop on Asian Translation to encourage the development of machine translation.",
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="doi-etal-2020-tddc">
<titleInfo>
<title>TDDC: Timely Disclosure Documents Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nobushige</namePart>
<namePart type="family">Doi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Oda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshiaki</namePart>
<namePart type="family">Nakazawa</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 describe the details of the Timely Disclosure Documents Corpus (TDDC). TDDC was prepared by manually aligning the sentences from past Japanese and English timely disclosure documents in PDF format published by companies listed on the Tokyo Stock Exchange. TDDC consists of approximately 1.4 million parallel sentences in Japanese and English. TDDC was used as the official dataset for the 6th Workshop on Asian Translation to encourage the development of machine translation.</abstract>
<identifier type="citekey">doi-etal-2020-tddc</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.459</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>3719</start>
<end>3726</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TDDC: Timely Disclosure Documents Corpus
%A Doi, Nobushige
%A Oda, Yusuke
%A Nakazawa, Toshiaki
%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 doi-etal-2020-tddc
%X In this paper, we describe the details of the Timely Disclosure Documents Corpus (TDDC). TDDC was prepared by manually aligning the sentences from past Japanese and English timely disclosure documents in PDF format published by companies listed on the Tokyo Stock Exchange. TDDC consists of approximately 1.4 million parallel sentences in Japanese and English. TDDC was used as the official dataset for the 6th Workshop on Asian Translation to encourage the development of machine translation.
%U https://aclanthology.org/2020.lrec-1.459
%P 3719-3726
Markdown (Informal)
[TDDC: Timely Disclosure Documents Corpus](https://aclanthology.org/2020.lrec-1.459) (Doi et al., LREC 2020)
ACL
- Nobushige Doi, Yusuke Oda, and Toshiaki Nakazawa. 2020. TDDC: Timely Disclosure Documents Corpus. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 3719–3726, Marseille, France. European Language Resources Association.