Weighted word2vec based on the distance of words.
Chia-Yang ChangShie-Jue LeeChih-Chin LaiPublished in: ICMLC (2017)
Keyphrases
- n gram
- related words
- english words
- unknown words
- word recognition
- word meaning
- word sense disambiguation
- word pairs
- weighted distance
- string edit distance
- linguistic information
- multiword
- word segmentation
- chinese word segmentation
- syntactic categories
- word frequencies
- keywords
- word similarity
- text corpus
- word spotting
- lexical information
- query words
- distance measure
- noun phrases
- latent topics
- speech recognition systems
- automatic transcription
- translation model
- handwritten words
- syntactic analysis
- lexical features
- training corpus
- natural language text
- co occurrence
- word level
- word co occurrence
- chinese text
- stop words
- spoken document retrieval
- word frequency
- distributional clustering
- word meanings
- frequency counts
- linguistic knowledge
- parallel corpus
- short list
- compound words
- punctuation marks
- out of vocabulary
- character recognition
- distance function
- text classification
- word order
- numeral strings
- handwritten documents
- handwriting recognition
- distance transform
- semantic similarity
- natural language processing