Titlebook: Natural Language Processing Using Very Large Corpora; Susan Armstrong,Kenneth Church,David Yarowsky Book 1999 Springer Science+Business Me

富饒

Prepositional Phrase Attachment Through a Backed-off Model,is applicable. Results on Wall Street Journal data of 84.5% accuracy are obtained using this method. A surprising result is the importance of low-count events — ignoring events which occur less than 5 times in training data reduces performance to 81.6%.

KEGEL

META

Obloquy

Trainable Coarse Bilingual Grammars for Parallel Text Bracketing,owledge of one language’s constraints to the task of bracketing the texts in both languages. The second approach generalizes the inside-outside algorithm to adjust the grammar parameters so as to improve the likelihood of a training corpus. Preliminary experiments on parallel English-Chinese text are supportive of these strategies.

GENRE

compassion

climax

RECUR

Statistical Augmentation of a Chinese Machine-Readable Dictionary,man evaluators and against a previously available dictionary. We also evaluated performance improvement in automatic Chinese tokenization. Results show that our method outputs legitimate words, acronymic constructions, idioms, names and titles, as well as technical compounds, many of which were lacking from the original dictionary.