Classifying New Words for Robust Parsing
Abstract
Robust natural language parsing systems must be able to handle words that are not in their lexicons. This paper describes a statistical classifier that determines the most likely parts of speech of new words. The classifier uses a loglinear model to obtain smoothed conditional probabilities that take into account the interactions between different features. We show accuracy results for this model, and compare it to some simpler methods.
Cite
Text
Franz. "Classifying New Words for Robust Parsing." Pre-proceedings of the Fifth International Workshop on Artificial Intelligence and Statistics, 1995.Markdown
[Franz. "Classifying New Words for Robust Parsing." Pre-proceedings of the Fifth International Workshop on Artificial Intelligence and Statistics, 1995.](https://mlanthology.org/aistats/1995/franz1995aistats-classifying/)BibTeX
@inproceedings{franz1995aistats-classifying,
title = {{Classifying New Words for Robust Parsing}},
author = {Franz, Alexander},
booktitle = {Pre-proceedings of the Fifth International Workshop on Artificial Intelligence and Statistics},
year = {1995},
pages = {226-232},
volume = {R0},
url = {https://mlanthology.org/aistats/1995/franz1995aistats-classifying/}
}