Choosing the Right Words: Characterizing and Reducing Error of the Word Count Approach.
H. Andrew SchwartzJohannes C. EichstaedtEduardo BlancoLukasz DziurzynskiMargaret L. KernStephanie RamonesMartin E. P. SeligmanLyle H. UngarPublished in: *SEM@NAACL-HLT (2013)
Keyphrases
- related words
- n gram
- english words
- word sense disambiguation
- word recognition
- word meaning
- word pairs
- unknown words
- word frequencies
- word segmentation
- lexical information
- text corpus
- word similarity
- keywords
- linguistic information
- spoken document retrieval
- word spotting
- multiword
- word co occurrence
- linguistic knowledge
- stop words
- noun phrases
- error rate
- chinese word segmentation
- frequency counts
- speech recognition systems
- wordnet
- syntactic categories
- query words
- handwritten words
- co occurrence
- word level
- training corpus
- numeral strings
- translation model
- latent topics
- word meanings
- punctuation marks
- word frequency
- out of vocabulary
- parallel corpus
- lexical features
- text corpora
- automatic transcription
- text documents
- semantic relatedness between words
- chinese text
- syntactic information
- handwriting recognition
- word sense
- character recognition
- semantic relations
- speech recognition
- natural language processing