ACL RD-TEC 1.0 Summarization of A94-1030
Paper Title:
IMPROVING CHINESE TOKENIZATION WITH LINGUISTIC FILTERS ON STATISTICAL LEXICAL ACQUISITION
IMPROVING CHINESE TOKENIZATION WITH LINGUISTIC FILTERS ON STATISTICAL LEXICAL ACQUISITION
Authors: Dekai Wu and Pascale Fung
Primarily assigned technology terms:
Other assigned terms:
- affix
- affixes
- bias
- bilingual corpus
- case
- characters
- chinese characters
- chinese text
- chinese words
- compounding
- compounds
- dictionary
- dictionary entries
- error rate
- evaluation method
- evaluation methodology
- evaluation paradigm
- hypothesis
- knowledge
- lexical entries
- lexical entry
- lexicon
- linguistic
- linguistic constraints
- linguistic knowledge
- meaning
- method
- methodology
- morpheme
- morphemes
- parallel bilingual corpus
- pause
- precision
- probabilities
- procedure
- process
- segments
- sentences
- suffixes
- syntactic constraints
- test data
- text
- training
- training corpus
- transcripts
- verb
- word
- words
