1. Task Outline and Evaluation Methods:

TSC2 consists of two tasks, task A and task B.

Task A (single document summarization)

Given the texts to be summarized and summarization lengthes, the participants

submit summaries for each text in plain text format.

This task is same as task A-2 in TSC-1.

Task B (multi-document summarization)

Given a set of texts, the participants produce summaries of it in plain text format. The information which was used to produce the document set, such as queries, as well as summarization lengthes are given to the participants.

The same evaluation methods (subjective and degree of modification) are used for both task A and task B.

Evaluation Method 1: subjective evaluation

First, four kinds of summaries are provided to human judges. They are the original text, human-produced summary, system summary, and summary produced by a baseline system. In subjective evaluation, the judges evaluate and rank them in one to four order, by examining how much the content of the text is covered and how readable the summary is.

Same evaluation was conducted at task A-2 in TSC-1.

○Evaluation Method 2: degree of modification

The judges modify the system summaries in terms of the content and readablity, after that, the degree of modification is measured.

3. Schedule:

2001.10	Dryrun
2001.11-12	Evaluation
2002.1	Analysis
2002.2	Round-Table
2002.4	Formal run
2002.5-6	Evaluation
2002.7	Analysis
2002.8	Round-Table
2002.10	Workshop

We will announce the task description in this page.

Takahiro FUKUSIMA (Otemon Gakuin University)
Hidetsugu NANBA (The Japan Society for the Promotion of Science)
Manabu OKUMURA (Tokyo Institute of Technology)