ACL RD-TEC 1.0 Summarization of C00-1057
Paper Title:
ROBUST SEGMENTATION OF JAPANESE TEXT INTO A LATTICE FOR PARSING
ROBUST SEGMENTATION OF JAPANESE TEXT INTO A LATTICE FOR PARSING
Authors: Gary Kacmarcik and Chris Brockett and Hisami Suzuki
Primarily assigned technology terms:
Other assigned terms:
- adjective
- adverb
- ambiguity
- ambiguous words
- approach
- bunsetsu
- canonical form
- case
- character type
- characters
- compounds
- corpora
- derivational morphology
- dictionary
- french
- heuristic
- heuristic rule
- heuristic rules
- heuristics
- inflected forms
- inflection
- input string
- japanese text
- kanji
- katakana
- knowledge
- large corpora
- lattice
- lemma
- lexical entries
- lexical entry
- lexicographic information
- lexicon
- lexicon entry
- linguistic
- linguistic information
- measures
- mechanisms
- nouns
- orthographic variation
- orthography
- parse
- parse time
- parser performance
- precision
- probabilities
- representations
- segmentation accuracy
- segments
- semantic
- semantic knowledge
- sentence
- sentences
- sparse data
- sparse data problem
- statistical models
- syntactic knowledge
- syntax
- system performance
- tagged corpus
- tags
- terms
- text
- tile system
- tree
- typographical errors
- verb
- vowel
- word
- word boundaries
- word candidate
- word lattice
- words
- writing system
