A Flexible POS tagger Using an Automatically Acquired Language Model

Details A Flexible POS tagger Using an Automatically Acquired Language Model A Flexible POS tagger Using an Automatically Acquired Language Model

1997-07-11

arxiv.org/abs/cmp-lg/9707003v1

Proceedings of EACL/ACL 1997, Madrid, Spain

Computer Science

Computation and Language

8 pages, aclap.sty, 2 eps figures. Appears in (E)ACL'97

Scientific paper

We present an algorithm that automatically learns context constraints using statistical decision trees. We then use the acquired constraints in a flexible POS tagger. The tagger is able to use information of any degree: n-grams, automatically learned context constraints, linguistically motivated manually written constraints, etc. The sources and kinds of constraints are unrestricted, and the language model can be easily extended, improving the results. The tagger has been tested and evaluated on the WSJ corpus.

Affiliated with

Also associated with

No associations

Rating

A Flexible POS tagger Using an Automatically Acquired Language Model does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with A Flexible POS tagger Using an Automatically Acquired Language Model, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Flexible POS tagger Using an Automatically Acquired Language Model will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-446661