Detecting new Chinese words from massive domain texts with word embedding.
Yu QianYang DuXiongwen DengBaojun MaQiongwei YeHua YuanPublished in: J. Inf. Sci. (2019)
Keyphrases
- chinese texts
- english words
- word segmentation
- unknown words
- chinese text
- chinese word segmentation
- n gram
- word recognition
- linguistic information
- natural language text
- keywords
- text corpus
- chinese english
- related words
- word sense
- syntactic analysis
- punctuation marks
- word sense disambiguation
- word meanings
- keyword extraction
- world knowledge
- lexical information
- training corpus
- semantic relatedness between words
- part of speech
- domain dependent
- word meaning
- text segments
- word similarity
- english chinese
- word pairs
- multiword
- word frequencies
- co occurrence
- language independent
- semantic relations
- english text
- word co occurrence
- text categorization
- natural language
- text documents
- query words
- spoken document retrieval
- pos tagging
- noun phrases
- word level
- text corpora