NTCIR Project
NTCIR-7 ACLIA
(
Advanced Cross-Lingual Information Retrieval and Question Answering )
Research Purpose Use of Test Collection

[JAPANESE] [NTCIR Home] [NTCIR Data Home]


NTCIR-7 ACLIA (Advanced Cross-Lingual Information Retrieval and Question Answering)   



NTCIR-7 ACLIA test collection can be used for experiments of Complex Question Answering and Information Retrieval between Chinese (Simplified (CS), Traditional (CT)), Japanese (JA), English (EN) such as


*"X-Y subtask" means to accept a question in language X and retrieve/extract answer in language Y.

The documents are full-text of news articles in CJK languages (except for English), which were published in Asian areas from 1998 to 2001. This test collection includes 100 Japanese topics (for JA-JA), 100 Simplified Chinese topics (for CS-CS) , 100 Traditional Chinese topics (for CT-CT), 300 English topics (100 for EN-JA, 100 for EN-CS and 100 for EN-CT), weighted answer nuggets, and answer-bearing document ID. In the IR4QA task, we shared the same topic set with CCLQA. The test collection also includes relevance judgement information for IR4QA evaluation.
Collection Task
Document Data Task Data
Genre Name Language Year Volume Size Question

Relevance judgment

Language #
NTCIR-7
ACLIA

QA

News articles

Xinhua (A)

Simplified Chinese

1998-2001

295,875 511 MB CJE EN-JA: 100
JA-JA: 100
EN-CS: 100
CS-CS: 100
EN-CT: 100
CT-CT: 100
Binary decision (system response conceptually containing the nugget or not)
Lianhe Zaobao (B)

Simplified Chinese

1998-2001

249,287 411 MB
CIRB20 (B)

Traditional Chinese

1998-1999

249,508 320 MB
CIRB40 (B) Traditional Chinese 2000-2001 901,446 582 MB
Mainichi (C) Japanese 1998-2001 419,759 544 MB

IR

News articles

Xinhua (A)

Simplified Chinese

1998-2001

295,875 511 MB CJE EN-JA: 98*
JA-JA: 98*
EN-CS: 97*
CS-CS: 97*
EN-CT: 95*
CT-CT: 95*
3-level relevance grading
Lianhe Zaobao (B)

Simplified Chinese

1998-2001

249,287 411 MB
CIRB20 (B)

Traditional Chinese

1998-1999

249,508 320 MB
CIRB40 (B) Traditional Chinese 2000-2001 901,446 582 MB
Mainichi (C) Japanese 1998-2001 419,759 544 MB

*Removed topics if no relevant document has been returned.

(A) --For the non-participants, Chinese Gigaword including Xinhua News Articles file is available from Linguistic Data Consortium (LDC). The format of the document records shall be converted with this perl script.
(B) NII delivers to non-participants for research purpose use.
(C) --For the non-participants, Mainichi Newspaper Japanese Article Data Full-Text Article Database CD-ROMs are available for research purpose use from Nichigai Associates and Mainichi Shinbum and the document records in the CD-ROMs shall be converted into the NTCIR standard record format by the script mai2.pl.(currently information is available in Japanese only).
To obtaib script mai2ntc-r.pl:http://research.nii.ac.jp/ntcir/permission/ntcir-4/script/mai2ntc-r.pl_txt
README (mai2ntc-r.pl) http://research.nii.ac.jp/ntcir/permission/ntcir-4/script/READMEforMainichiScript-r.txt



The documents sets included in the NTCIR-7 ACLIA test collection are as follows.

A.1 Chinese Data Set (Simplified)

Xinhua (Copyright: Xinhua News Agency) 1998-2001

Lianhe Zaobao (Copyright: Singapore Press Holdings Limited) 1998-2001

A.2 Chinese Data Set (Traditional)

CIRB020: United Daily News, Economic Daily News, Min Sheng Daily, United Evening News, Star News (Copyright: UDN.COM) 1998-1999 

CIRB40: United Daily News, United Express, Ming Hseng News, Economic Daily News (Copyright: UDN.COM news agency) 2000-2001 

A.3 Japanese Data Set

Mainichi News Paper (Copyright: Mainichi Newspapers Co. Ltd.) 1998-2001
 

Tags

Tags are based on the TREC format.

Mandatory tags

<DOC>

</DOC>

The tag for each document

<DOCNO>

</DOCNO>

Document identifier

<LANG>

</LANG>

Language code: ZH, EN, JA,KR

<HEADLINE>

</HEADLINE>

Title of this news article

<DATE>

</DATE>

Issue date

<TEXT>

</TEXT>

Text of news article

Optional tags

<P>

</P>

Paragraph marker

<SECTION>

</SECTION>

Section identifier in original newspapers

<AE>

</AE>

Contain figures or not

<WORDS>

</WORDS>

Number of words in 2 bytes

Format

Question Format

Example Question

<TOPIC_SET>

  <METADATA>
    <DESCRIPTION>NTCIR-7 ACLIA Training questions</DESCRIPTION>
    <VERSION>v20071116</VERSION>
    <LANGUAGE TARGET="JA" />
    <CORPUS>Mainichi Newspaper (1998-2001)</CORPUS>
  </METADATA>
  
  <TOPIC ID="ACLIA1-JA-T1">
    <QUESTION LANG="EN"><![CDATA[What is Fatah?]]></QUESTION>
    <QUESTION LANG="JA"><![CDATA[ファタハとはどんな組織ですか?]]></QUESTION>
    <NARRATIVE LANG="EN"><![CDATA[The analyst is especially interested in major characteristics of the organization called Fatah.]]></NARRATIVE>
    <NARRATIVE LANG="JA"><![CDATA[ファタハの一般的な情報と活動内容についての回答を求めています。]]></NARRATIVE>
  </TOPIC>
  
</TOPIC_SET>


For more details about the question format, visit this page.

Gold Standard

Example Gold Standard

<TOPIC_SET>
  <METADATA>
    <DESCRIPTION>NTCIR-7 ACLIA Training questions and answers</DESCRIPTION>
    <VERSION>v20071116</VERSION>
    <LANGUAGE TARGET="JA" />
    <CORPUS>Mainichi Newspaper (1998-2001)</CORPUS>
  </METADATA>
  
  <TOPIC ID="ACLIA1-JA-T1" TITLE="ファタハ">
    <QUESTION LANG="EN"><![CDATA[What is Fatah?]]></QUESTION>
    <QUESTION LANG="JA"><![CDATA[ファタハとはどんな組織ですか?]]></QUESTION>
    <ANSWERTYPE>DEFINITION</ANSWERTYPE>
    <NARRATIVE LANG="EN"><![CDATA[The analyst is especially interested in major characteristics of the organization called Fatah.]]></NARRATIVE>
    <NARRATIVE LANG="JA"><![CDATA[ファタハの一般的な情報と活動内容についての回答を求めています。]]></NARRATIVE>
    <ANSWER>
      <TEXT ID="1" DOCNO="JA-010101032"><![CDATA[パレスチナ解放機構(PLO)の主流派ファタハ]]></TEXT>
      <TEXT ID="2" DOCNO="JA-011218020"><![CDATA[ファタハが反イスラエル抵抗闘争の主体となっている]]></TEXT>
      <TEXT ID="3" DOCNO="JA-211221040"><![CDATA[アラファト議長の最大支持基盤であるファタハは13日、]]></TEXT>
      <NUGGET ID="1" VITAL="10" NONVITAL="0" SCORE="1.0"><![CDATA[パレスチナ解放機構(PLO)主流派]]></NUGGET>
      <NUGGET ID="2" VITAL="3" NONVITAL="7" SCORE="0.3"><![CDATA[反イスラエル抵抗闘争の主体となっている]]></NUGGET>
      <NUGGET ID="3" VITAL="9" NONVITAL="1" SCORE="0.9"><![CDATA[アラファト議長の最大支持基盤]]></NUGGET>
    </ANSWER>
  </TOPIC>
  
</TOPIC_SET>


For more details about the question format, visit this page.

 

The followings are the procedures to obtain this NTCIR-7 ACLIA test collection. The test collection and data available from NII are free of charge.


Task Data ( without document data )


Document Data

Please read "The terms of use" carefully before you apply data.
Documents to submit


Reference


Address
NTCIR Project (Rm.1309)
National Institute of Informatics
2-1-2 Hitotsubashi Chiyoda-ku, Tokyo
102-8430, JAPAN
PHONE: +81-3-4212-2750
FAX: +81-3-4212-2751
Email: ntc-secretariat


Notice

The test collection has been constructed and used for the NTCIR. They are usable only for the research purpose use.
The documents collection included in the test collection were provided to NII for used in NTCIR free of charge or for a fee. The providers of the document data kindly understand the importance of the test collection in the research on information access technologies and then granted the use of the data for research purpose. Please remember that the document data in the NTCIR test collection is copyrighted and has commercial value as data. It is important for our continued reliable and good relationship with the data producers/providers that we researchers must behave as a reliable partners and use the data only for research purpose under the user agreement and use them carefully not to violate any rights for them .