[Asis-l] CFP: TREC Genomics Pre-Track workshop

[William Hersh]

CALL FOR PARTICIPATION

TEXT RETRIEVAL CONFERENCE (TREC) GENOMICS PRE-TRACK WORKSHOP

To be held at:  Joint Conference on Digital Libraries (JCDL) 2002 (www.jcdl2002.org)

Thursday, July 18, 2002
Lloyd Center Doubletree Hotel
Portland, Oregon, USA

William Hersh, Workshop Chair, hersh at ohsu.edu

The goal of this workshop is to allow individuals interested in the Text Retrieval Conference (TREC, trec.nist.gov) Genomics Pre-Track to come together to discuss common goals and interests for the pre-track.  The workshop will be designed to generate a plan for developing a common set of tasks, databases, and evaluation measures for the pre-track.  The morning will be devoted to presentations by attendees aimed at allowing various communities (IR/digital library and genomics/bioinformatics) to get to know each other's research interests and goals.  The afternoon will be geared towards developing a plan for the pre-track, with the structure based on the number of attendees (i.e., if attendance is large, we will break into small groups).

Background:

The Text Retrieval Conference (TREC, trec.nist.gov) is an annual activity of the information retrieval (IR) community aiming to evaluate IR systems and users.  It is sponsored by the National Institute for Standards and Technology (NIST).  IR has historically focused on document retrieval, but the field has expanded in recent years with the growth of new information needs (e.g., question-answering, multi-lingual) and platforms (the Web).  A key feature of TREC is that research groups work on a common source of data and a common set of queries or tasks.  The goal is to allow comparisons across systems and approaches in a research-oriented, collegial manner.

In recent years, interest at TREC has also grown to other types of data besides textual documents, such as video.  Another category of data that participants are interested in is structured data, and one interest within that category is genomics data.

At the same time, the growing field of bioinformatics has begun to take an interest in a number of IR-related issues.  Interest is particularly high in information extraction (IE), an area related to IR and one in which many IR researchers have worked.

Thus the time seems ripe to foster collaboration across these communities.  The TREC activity is organized into "tracks" of common interest, such as question-answering, multi-lingual IR, Web searching, and interactive retrieval.  TREC generally works on an annual cycle, with data distributed in the spring, experiments run in the summer, and the results presented at the annual conference which usually takes place in November.  TREC also has a notion of exploratory efforts, called "pre-tracks."

For TREC 2002, there will be a "Genomics Pre-Track."  The current plan is to devote the TREC 2002 pre-track to assembling an information collection and set of queries/tasks.  There will be challenges to finding common ground across the IR and bioinformatics communities, i.e., balancing the domain-specific needs of the latter with the aim for generalizability for the former.

The objectives of this workshop will therefore be to:
1.  Allow the IR/digital library and genomics/bioinformatics communities become familiar with each other through a series of presentations on past work, current interests, and future goals.
2.  Have discussion on how to proceed with the pre-track, in particular focusing on the IR/IE tasks, databases and other resources to use, and evaluation measures.

Workshop Schedule:

8:30-9:00 - Welcome, introductions, overview of TREC - Bill Hersh

9:00-10:00 - Research-oriented talks

Alex Morgan - Evaluating Genomics Text Retrieval and Information Extraction Systems:  Some Lessons Learned
See-Kiong Ng - Extracting Bio-Molecular Interaction Pathway Information from Online Scientific Literature
Alan Aronson - Augmenting the UMLS Metathesaurus with Gene Terminology
Dat Tran - Toward an Ontology of Information Retrieval Needs of Researchers in Genomics and Proteomics

10:00-10:30 - Break

10:30-11:30 - Proposal-oriented talks

Hsin-Hsi - NTU Proposal for TREC Genomics Pre-Track Workshop
Jean-Pierre Chanod - A Contribution to TREC Genomics Pre-Track
Rik Belew - Connecting Text Search to the Rest of the Task:  Position Paper for TREC/Genomic Track Workshop
Dina Demner-Fushman - Genomic Entity Recognition at TREC

11:30-Noon - Goal-setting and general planning for the afternoon

Noon-1:30 - Lunch

1:30-1:45 - Welcome to TREC - Ellen Voorhees, TREC Chair

1:45 - 5:00 - General planning for pre-track activities centered around task, collection, and evaluation measures

Registration:

Attendance at the workshop is open to anyone with an interest in this area.  To attend, you must register for the workshop at the JCDL 2002 Web site (www.jcdl2002.org).  You do not need to register for the full JCDL conference (though are encouraged to do so and attend!).