Call For Papers

 

Translating Biology: Text Mining Tools That Work

 

A Pacific Symposium on Biocomputing Session

 

January 4-8, 2008

The Big Island, Hawai'i

 

http://psb.stanford.edu/cfp-nlp.html

 

Biomedical science is now an information-intensive field of study, with

high-throughput experimental techniques generating large amounts of data, and

bioinformatics providing tools for managing and making sense of that data.

However, the information generated and used in biomedical science must be

accessible both to computers and to people. This requires constant translation

between human-readable forms, such as text and figures, to computer-readable

forms, such as biological databases and ontologies. In a recent PLoS

Computational Biology editorial, Philip Bourne posed the following question:

Will a biological database be different from a biological journal? If we had

text mining tools that worked, then the translation from text to database (and

back) would blur these lines. Such tools would enable the seamless incorporation

of semantic information extracted from text with databases and with analytical

tools, as just one of many sources of information for addressing complex

biological problems.

 

From the many publications in the area, we know that performance has reached

reasonable levels on a number of basic text mining tasks, such as indexing and

the identification of biomedical entities. We now need to ask a new set of

questions: Do these tools work? Can they be adapted to new applications? Are

they cost-effective in real applications? Who uses these tools, and how? Can

these tools be maintained over time? The answers to these questions are critical

to understanding the apparent gap between the number of publications on

biomedical text mining and the number of deployed text mining applications. The

answers to these questions are also essential to providing the bioinformatics

community with the text mining tools that they are asking for. We categorize

these questions into four attributes: utility, usability, portability, and

robustness.

 

The proposed session will focus on papers that explore these issues, including

questions such as: 

 

 

What is the actual utility of text mining in the work flows of the various

communities of potential users—model organism database curators, bedside

clinicians, biologists utilizing high-throughput experimental assays, hospital

billing departments?

 

How usable are biomedical text mining applications? How does the application

fit into the workflow of a complex bioinformatics pipeline? What kind of

training does a bioscientist require to be able to use an application?

 

Is it possible to build portable text mining systems? Can systems be adapted

to specific domains and specific tasks without the assistance of an

experienced language processing specialist?

 

How robust and reliable are biomedical text mining applications? What are the

best ways to assess robustness and reliability? Are the standard evaluation

paradigms of the natural language processing world—intrinsic evaluation

against a gold standard, post-hoc judging of outputs by trained judges,

extrinsic evaluation in the context of some other task—the best evaluation

paradigms for biomedical text mining, or even sufficient evaluation paradigms?

 

Session chairs

 

Lynette Hirschman, The MITRE Corporation

 

Kevin Bretonnel Cohen (Contact person)

University of Colorado School of Medicine

kevin.cohen@gmail.com

 

Philip Bourne

University of California San Diego

 

Hong Yu

University of Wisconsin at Milwaukee

 

Submission information

 

The core of the conference consists of rigorously peer-reviewed full-length

papers reporting on original work. Accepted papers will be published in a

hard-bound archival proceedings, and the best of these will be presented orally

to the entire conference. Researchers wishing to present their research without

official publication are encouraged to submit a one-page abstract by noon,

November 9, 2007 to present their work in the poster sessions.

 

Important dates

 

Paper submissions due: July 16, 2007

Notification of paper acceptance: September 5, 2007

Final paper deadline: September 24, 2007 midnight PT

Abstract deadline: November 9, 2007

Meeting: January 4-8, 2008

 

For full submission information, including style sheets and

all requirements, please see the session web site at

http://psb.stanford.edu/cfp-nlp.html.