| 1 |
Journal of Machine Learning Research 2 (2002) 669--693 Submitted 9/01; Published 3/02 Learning Rules and Their Exceptions
|
|
|
|
In: http://lcg-www.uia.ac.be/lcg/texts/./ps/dejean.jmlr2002.ps.gz (2002)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Learning rules and their exceptions
|
|
|
|
In: http://jmlr.csail.mit.edu/papers/volume2/dejean02a/dejean02a.pdf (2002)
|
|
Abstract:
We present in this article a top-down inductive system, ALLiS, for learning linguistic structures. Two difficulties came up during the development ofthe system: the presence ofa significant amount ofnoise in the data and the presence ofexceptions linguistically motivated. It is then a challenge for an inductive system to learn rules from this kind ofdata. This leads us to add a specific mechanism, refinement, which enables learning rules and their exceptions. In the first part ofthis article we evaluate the usefulness ofthis device and show that it improves results when learning linguistic structures. In the second part, we explore how to improve the efficiency ofthe system by using prior knowledge. Since Natural Language is a strongly structured object, it may be important to investigate whether linguistic knowledge can help to make natural language learning more efficiently and accurately. This article presents some experiments demonstrating that linguistic knowledge improves learning. The system has been applied to the shared task of the CoNLL’00 workshop.
|
|
Keyword:
Chunking; Learning Exceptions; Natural Language Processing; Rule Induction; Symbolic Learning
|
|
URL: http://jmlr.csail.mit.edu/papers/volume2/dejean02a/dejean02a.pdf
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.88.9409
|
|
BASE
|
|
Hide details
|
|
|
|
|
