SHACHI - Language Resource Metadata Database

The NTCIR project is a series of on-going evaluation workshops designed to enhance research in Information Access (IA) technologies including information retrieval, question answering, and text summarization/extraction. The IR Test collection includes (1) Document data (about 330,000 documents, more than half of them are English-Japanese paired), (2) 83 Search topics (Japanese), and (3) Relevance Judgements. The Collection also contains the Term Extraction Test collection, a tagged corpus using the 2000 Japanese documents selected from the above IR test collection.

The NTCIR project is a series of on-going evaluation workshops designed to enhance research in Information Access (IA) technologies including information retrieval, question answering, and text summarization/extraction. The Collection includes (1) Document data (about 5300,000 documents including about 400,000 Japanese and 130,000 English documents), (2) 49 Search topics (Japanese and English), and (3) Relevance Judgements. For experiments, the document data must be used with those of the NTCIR-1.

The NTCIR project is a series of on-going evaluation workshops designed to enhance research in Information Access (IA) technologies including information retrieval, question answering, and text summarization/extraction. The Collection is for the automatic text summarization task and it includes : (1) Document data (Japanese newspaper articles from Mainichi Newspaper) and (2) Model Summaries (Japanese. For each of 180 documents, 7 types of single document summaries prepared in different length by different strategies were prepared by 3 analysts). Note that the NII provides only model summaries, therefore, each purchaser needs to obtain the document data from Mainichi Newspaper Co.

The NTCIR project is a series of on-going evaluation workshops designed to enhance research in Information Access (IA) technologies including information retrieval, question answering, and text summarization/extraction. The Collection is for the automatic text summarization task and it includes : (1) Document data (Japanese newspaper articles from Mainichi Newspaper) and (2) Model Summaries (Japanese. 2 types of single document summaries for each of 1000 documents). Distribution of NTCIR-2 SUMM TAO Collection is currently unavailable (as of February, 2009).

The NTCIR project is a series of on-going evaluation workshops designed to enhance research in Information Access (IA) technologies including information retrieval, question answering, and text summarization/extraction. The Collection includes (1) Document data (Mainichi Newspaper (Japanese), Chinese news articles published in Taiwan including United Daily, Mainichi Daily newspaper (English), English news articles published in Taiwan, and Korean Economic Daily (Korean)), (2) Search topics (Chinese/Korean/Japanese/English), and (3) Relevance Judgements. Note that the NII provides only the Topics and Relevance Judgments, Mainichi Daily (English document), and CIRB020 (Chinese document). The Japanese document data can be obtained from Nichigai Associates, Inc., Japan.

The NTCIR project is a series of on-going evaluation workshops designed to enhance research in Information Access (IA) technologies including information retrieval, question answering, and text summarization/extraction. This collection consists of newspaper articles and question/answer data used for the NTCIR-3 QAC (Question Answering Challenge) task. Answers include names and numerical/time expressions. Note that the NII will provide newspaper articles only for task participants.

The NTCIR project is a series of on-going evaluation workshops designed to enhance research in Information Access (IA) technologies including information retrieval, question answering, and text summarization/extraction. The Collection is for the automatic text summarization task and it includes : (1) Document data (Japanese newspaper articles from Mainichi Newspaper) and (2) two types of Model Summaries (single document summaries and multi-document summaries. Note that the NII provides only model summaries, therefore, each purchaser needs to obtain the document data from Mainichi Newspaper Co.