A Sample of A Japanese Topic

<TITLE>
母集団モデル
</TITLE>

<DESCRIPTION>
計量書誌学分野で、標本データでは観察されない研究者あるいは論文の扱いに付いて論じたものはないか。
</DESCRIPTION>

<NARRATIVE>
収集された標本データについての属性を統計的に論じたものは多いが、計量書誌学（研究者と論文の関係、論文と雑誌の関係を扱っているものがよい）では、実際に標本には現れないデータをいかにして扱えばよいかを論じたものがあるのかどうか知りたい。ロトカの法則やブラッドフォードの法則の、母集団モデルへの展開を考えたものがあるといちばん良い。
</NARRATIVE>

<CONCEPT>
a. 計量書誌学,
b. 未知データ,
c. 母集団, 標本,
d. ロトカの法則, ブラッドフォードの法則
</CONCEPT>

A search topic is a formatted description of a user's search request. Format of the topics is similar to the one used in TREC and contains SGML-like tags.

A topic consists of TITLE of the topic, DESCRIPTION, detailed NARRATIVE, a list of CONCEPTS, and a list of FIELD(S).
<TOPIC q=nnnn> indicates the start of a search topic. Four-digit numbers, nnnn indicates the number of the TOPIC.
TITLE is a very short description of the topic. Originally it is intended to use as a nickname of the topic; It may not contain every concepts needed to represent the search request. However it may be also used as a very short query which resembles the one often submitted by an end-user of internet search engines.
DESCRIPTION is a natural language description of a search request.
Each NARRATIVE may contain detailed explanation of the topic, term definition, background knowledge, purpose of the search, expected number of relevant documents, preference in text types, criteria of relevance judgment, and so on. They may be used as a profile of user's information need in a specific situation to evaluate interactive retireval systems.
Each line in the field of the CONCEPT represents a group of similar concepts. A line of concepts start with a label such as; a., b., c., and so on.
The FIELD is not used in relevance assessment. A paper published by an academic society other than the field(s) listed in the FILED may be relevant.
</TOPIC> is a tag represent the end of a search topic.
In the Workshop, a participant group can submit the results of more than one run.
Queries (search statement) can either be constructed automatically from the topics, or can be manually constructed.
In the case of automatic query construction, the participants must submit the results of the searches using only "DESCRIPTION" fields of the topics as the mandatory run. As results of the opitional runs, any fields of the topics can be used to construct queries.
In the case of manual query construction, any fields of the topics can be used in the search.