Grammatical category disambiguation by statistical optimization
Computational Linguistics
A Cache-Based Natural Language Model for Speech Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Portability in the Janus Natural Language Interface
HLT '89 Proceedings of the workshop on Speech and Natural Language
A stochastic parts program and noun phrase parser for unrestricted text
ANLC '88 Proceedings of the second conference on Applied natural language processing
ACL '90 Proceedings of the 28th annual meeting on Association for Computational Linguistics
Unification-based semantic interpretation in the BBN Spoken Language System
HLT '89 Proceedings of the workshop on Speech and Natural Language
Preference semantics for message understanding
HLT '89 Proceedings of the workshop on Speech and Natural Language
Augmenting a hidden Markov model for phrase-dependent word tagging
HLT '89 Proceedings of the workshop on Speech and Natural Language
Shipping departments vs. shipping pacemakers: using thematic analysis to improve tagging accuracy
AAAI'92 Proceedings of the tenth national conference on Artificial intelligence
Probabilistic parse scoring with prosodic information
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II
Analysis of inconsistencies in cross-lingual automatic ToBI tonal accent labeling
TSD'11 Proceedings of the 14th international conference on Text, speech and dialogue
Ending-based strategies for part-of-speech tagging
UAI'94 Proceedings of the Tenth international conference on Uncertainty in artificial intelligence
Cross-lingual English Spanish tonal accent labeling using decision trees and neural networks
NOLISP'11 Proceedings of the 5th international conference on Advances in nonlinear speech processing
| Hi-index | 0.01 |
We report here on our experiments with POST (Part of Speech Tagger) to address problems of ambiguity and of understanding unknown words. Part of speech tagging, perse, is a well understood problem. Our paper reports experiments in three important areas: handling unknown words, limiting the size of the training set, and returning a set of the most likely tags for each word rather than a single tag. We describe the algorithms that we used and the specific results of our experiments on Wall Street Journal articles and on MUC terrorist messages.