*****  To join INSNA, visit  *****

                     Clairlib, The Clair Library

                    version 0.953 is now available



The University of Michigan's CLAIR (Computational Linguistics And
Information Retrieval) group is happy to present the second release of
clairlib, the Clair library.

The Clair library is intended to simplify a number of generic tasks in
Natural Language Processing (NLP) and Information Retrieval (IR), with
additional applications to Bioinformatics and Political Science. Its
architecture also allows for external software to be plugged in with
very little effort.

Clairlib features a tiered architecture with a core shared by all
applications and subject-specific libraries (currently in political
science and bioinformatics).


Native: Tokenization, Summarization, LexRank, Biased LexRank, Document
Clustering, Document Indexing, PageRank, Web Graph Analysis,
Bioinformatics Text Analysis, Political Science Text Analysis

Imported: Stemming, Sentence segmentation, Web page download, Web


Write to [log in to unmask] to get a beta copy.


This work has been supported in part by grants R01 LM008106
"Representing and Acquiring Knowledge of Genome Regulation" and U54
DA021519 "National center for integrative bioinformatics", both from the
National Institutes of Health as well as grants IDM 0329043 
"Probabilistic and link-based Methods for Exploiting Very Large Textual 
Repositories" and DHB 0527513 "The Dynamics of Political Representation 
and Political Rhetoric," both from the National Science Foundation.


The Clair Library is developed by the Clair group at the University of

Project design: Dragomir Radev
Main implementers: Anthony Fader, Mark Hodges, and Dragomir Radev
Additional code by: Timothy Allison, Michael Dagitses, Aaron Elkiss,
Gunes Erkan, Scott Gifford, Mark Joseph, Samuela Pollack, and Adam

SOCNET is a service of INSNA, the professional association for social
network researchers ( To unsubscribe, send
an email message to [log in to unmask] containing the line
UNSUBSCRIBE SOCNET in the body of the message.