Handling Missing Words by Mapping Across Word Vector Representations.
Rajendra BanjadeNabin MaharjanDipesh GautamVasile RusPublished in: FLAIRS Conference (2016)
Keyphrases
- n gram
- related words
- english words
- word recognition
- word sense disambiguation
- word pairs
- word meaning
- word frequencies
- word segmentation
- vector representation
- unknown words
- lexical information
- multiword
- word similarity
- syntactic categories
- linguistic knowledge
- stop words
- text corpus
- latent topics
- spoken document retrieval
- linguistic information
- query words
- word spotting
- chinese word segmentation
- natural language text
- word meanings
- keywords
- numeral strings
- feature vectors
- automatic transcription
- co occurrence
- frequency counts
- printed text
- document representation
- word co occurrence
- missing values
- missing data
- speech recognition systems
- punctuation marks
- distributional clustering
- compound words
- word frequency
- language specific
- word sense
- lexical features
- out of vocabulary
- short list
- handwritten words
- word order
- text corpora
- historical manuscripts
- part of speech
- language independent
- semantic relations
- language model
- word clouds
- natural language processing