, 34, 1-3, Feb. 1999,
Special Issue on Natural Language Learning
Cardie, Cornell University, email@example.com
Raymond J. Mooney,
University of Texas at Austin, firstname.lastname@example.org
The application of learning techniques to natural language processing has grown
dramatically in recent years under the rubric of "corpus-based," "statistical,"
or "empirical" methods. However, most of this research has been conducted
outside the traditional machine learning research community. This special
issue is an attempt to bridge this divide by gathering together a variety of
recent research papers on various aspects of natural language learning - many
from authors who do not generally publish in the traditional machine learning
literature - and making them available to the readers of Machine Learning.
The special issue appears as Machine Learning 34, 1-3, February
1999. From 31 original submissions, 9 papers were accepted for publication in
the special issue. We hope that it becomes an influential issue of the journal
and improves the communication and exchange of ideas between machine learning
and natural language researchers.
Table of Contents
- "Guest Editors' Introduction: Machine Learning and Natural Language"
Cardie and Raymond
J. Mooney ( postscript )
"Forgetting Exceptions is Harmful in Language Learning,"
Walter Daelemans, Antal van den Bosch, & Jakub Zavrel
"Similarity-Based Models of Word Cooccurrence Probabilities,"
Lillian Lee, &
"An Efficient, Probabilistically Sound Algorithm for Segmentation and Word Discovery,"
Michael R. Brent
"A Winnow-Based Approach to Context-Sensitive Spelling Correction,"
Andrew R. Golding &
"Using Decision Trees to Construct a Practical Parser,"
Masahiko Haruno, Satoshi Shirai, Yoshifumi Ooyama, & Hiroshi Aizawa,
"Learning to Parse Natural Language with Maximum Entropy Models,"
"Statistical Models for Text Segmentation,"
Doug Beeferman, Adam Berger, & John Lafferty
"An Algorithm that Learns What's in a Name," Daniel Bikel, Richard
Schwartz, & Ralph M. Weischedel (abstract)
"Learning Information Extraction Rules for Semi-Structured and Free Text,"
Call for Papers
Original Call for Papers (deadline long since past)