ACL RD-TEC 1.0 Summarization of P98-2206
Paper Title:
CHINESE WORD SEGMENTATION WITHOUT USING LEXICON AND HAND-CRAFTED TRAINING DATA
CHINESE WORD SEGMENTATION WITHOUT USING LEXICON AND HAND-CRAFTED TRAINING DATA
Authors: Maosong Sun and Dayang Shen and Benjamin K. Tsou
Primarily assigned technology terms:
Other assigned terms:
- annotated corpus
- approach
- bias
- bigram
- break
- case
- characters
- chinese characters
- chinese corpora
- chinese corpus
- chinese word
- concepts
- conditional probability
- corpora
- distribution
- english corpus
- experimental results
- fact
- human judgment
- hypotheses
- hypothesis
- information theory
- knowledge
- language information
- lexicon
- linguistic
- linguistic resources
- local maximum
- measure
- measures
- method
- mutual information
- news corpus
- nlp applications
- nouns
- probability
- segmentation accuracy
- segmented corpus
- sentence
- sentences
- standard deviation
- statistical data
- statistics
- tag set
- tagged corpus
- terms
- theory
- training
- training corpus
- training data
- word
- word formation
- words
