Determining the Characteristic Vocabulary for a Specialized Dictionary using Word2vec and a Directed Crawler.
Gregory GrefenstetteLawrence MuchemiPublished in: CoRR (2016)
Keyphrases
- search engine
- compound words
- keywords
- text corpus
- out of vocabulary
- bilingual dictionaries
- general purpose
- n gram
- parallel corpus
- english words
- web pages
- spoken term detection
- training corpus
- word sense disambiguation
- co occurrence
- website
- multiword
- word pairs
- noun phrases
- named entities
- sparse representation
- face recognition