3716 search results - page 226 / 744 » On the monotonization of the training set |
161
click to vote
ACL
2004
15 years 8 months ago
2004
Supervised learning methods for WSD yield better performance than unsupervised methods. Yet the availability of clean training data for the former is still a severe challenge. In ...
133
click to vote
ACL
2006
15 years 8 months ago
2006
The present work advances the accuracy and training speed of discriminative parsing. Our discriminative parsing method has no generative component, yet surpasses a generative base...
141
click to vote
ACL
2006
15 years 8 months ago
2006
We present a novel classifier-based deterministic parser for Chinese constituency parsing. Our parser computes parse trees from bottom up in one pass, and uses classifiers to make...
182
click to vote
EMNLP
2004
15 years 8 months ago
2004
This paper explores the large-scale acquisition of sense-tagged examples for Word Sense Disambiguation (WSD). We have applied the "WordNet monosemous relatives" method t...
175
click to vote
FLAIRS
2004
15 years 8 months ago
2004
We illustrate that Web searches can often be utilized to generate background text for use with text classification. This is the case because there are frequently many pages on the...