INTRODUCTION:

The NTCIR is a series of evaluation workshop to enhance the research in information access technologies, including text retrieval, cross-lingual information access, question answering, etc, by providing re-usable test collections, evaluation infrastructures, and a forum of researchers. The emphasis has been placed on, but not limited to, Japanese and other Asian languages, and cross-lingual applications between Asian languages and English. The workshops are periodical events which are held once per about one and a half years (about 18 months).

The detailed task and collection description will be available in each task's web site.

TASKS:

The 5th NTCIR Workshop selected the following 5 areas of research as "Tasks" and 1 area as "pilot task"; For details, please visit each task's call for participation below.

1. Cross-Lingual Information Retrieval Task (CLIR)

Multilingual CLIR

Bilingual CLIR and Pivot Bilingual CLIR, and

Single language IR

Languages: Traditional Chinese, Korean, English and Japanese

2. Cross-Language Question Answering Task (CLQA)

CLQA is a new task based on CLIR and QAC

5 subtasks (C->C, E->C, C->E, E->J, J->E) are provided (J->J will is provided in QAC).

3. Patent Retrieval Task (PATENT)

Retrieval task: "Invalidity search"

Classification task: The purpose is to categorize target patent applications based on the F-term classification system.

4. Question Answering Task (QAC)

In a simulated interactive situation, all and only correct answers should be listed as its response for each question.

Task for reference evaluation: all references are resolved manually and the questions are made understandable in isolation.

5. Web Task (WEB)

Navigational Retrieval Task: known item search

pilot task: Query Term Expansion Task

6. Pilot Workshop: Multimodal Summarization of Trend Information (MuST)�@--Japanese only

TEST COLLECTIONS:

NTCIR-4 CLIR used Traditional Chinese, Korean, Japanese, English documents published in East Asia in 1998-1999. NTCIR-5 CLIR add Chinese, Korean and Japanese (in 2000-2001) newspaper articles, so the size of the document collections are increased. NTCIR-3 CLIR and NTCIR-4 CLIR, the test collections used in CLIR at NTCIR-3 and NTCIR-4, are provided as training collections (including the document collections).

CLQA uses Chinese, Japanese, English newspaper articles published in 2000-2001.

NTCIR-5 PATENT uses the same test collection as NTCIR-4 PATENT. NTCIR-3 PATENT and NTCIR-4 PATENT, the test collection used in PATENT at NTCIR-3 and NTCIR-4 are available for training (user agreement form is required).

NTCIR-4 QAC used Japanese newspaper articles published in 1998-1999, and the size of the document at NTCIR-5 QAC is increased to 1998-2001.NTCIR-4 QAC, the test collections used in QACR at NTCIR-4, is provided as training collections (including the document collections).

WEB uses NW1000G-04. NTCIR-3 WEB and NTCIR-4 WEB, the test collection used in WEB at NTCIR-3 and NTCIR-4 are available for training (user agreement form is required).

HOW TO PARTICIPATE:

Please consult How to Participate. Online registration form is linked from the "How to Participate"

IMPORTANT DATES:

ntc-admin
This page started on : 2005-12-15