Multidimensional Transformation-Based Learning

Computer Science – Computation and Language

Scientific paper

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

8 pages, 2 figures, presented at CONLL 2001

Scientific paper

This paper presents a novel method that allows a machine learning algorithm following the transformation-based learning paradigm \cite{brill95:tagging} to be applied to multiple classification tasks by training jointly and simultaneously on all fields. The motivation for constructing such a system stems from the observation that many tasks in natural language processing are naturally composed of multiple subtasks which need to be resolved simultaneously; also tasks usually learned in isolation can possibly benefit from being learned in a joint framework, as the signals for the extra tasks usually constitute inductive bias. The proposed algorithm is evaluated in two experiments: in one, the system is used to jointly predict the part-of-speech and text chunks/baseNP chunks of an English corpus; and in the second it is used to learn the joint prediction of word segment boundaries and part-of-speech tagging for Chinese. The results show that the simultaneous learning of multiple tasks does achieve an improvement in each task upon training the same tasks sequentially. The part-of-speech tagging result of 96.63% is state-of-the-art for individual systems on the particular train/test split.

No associations

LandOfFree

Say what you really think

Search LandOfFree.com for scientists and scientific papers. Rate them and share your experience with other people.

Rating

Multidimensional Transformation-Based Learning 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 Multidimensional Transformation-Based Learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Multidimensional Transformation-Based Learning will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFWR-SCP-O-642654

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.