An Integrated Neuro and Rule-based Part of Speech Tagger

摘要

So far, the neuro part of speech tagger that uses different lengths of contexts based on longest context priority and takes into account the maximization of information amount have been proposed for the purposed of constructing a practical tagger which uses as few training data as possible. The proposed neuro tagger has tagging accuracy of 94.4/100 (for accounting only the ambiguous words in part of speech), when a small Thai corpus with ten thousand order words was used for training.