Assessing the Corpus Size vs. Similarity Trade-off for Word Embeddings in Clinical NLP.
Kirk RobertsPublished in: ClinicalNLP@COLING 2016 (2016)
Keyphrases
- trade off
- word pairs
- word frequencies
- word sense disambiguation
- distance measure
- similarity measure
- coreference resolution
- noun phrases
- semantic similarity
- co occurrence
- sentence level
- question answering
- vector space
- natural language processing
- information extraction
- natural language text
- word similarity
- lexical features
- reference resolution
- word co occurrence
- computational linguistics
- multiword
- semantic analysis
- statistical machine translation
- training corpus
- text corpus
- linguistic information
- information retrieval
- grammar induction
- wordnet
- dimensionality reduction
- text mining
- parallel corpus
- tasks in natural language processing
- sentence similarity
- natural language
- pos taggers
- sentiment analysis
- unknown words
- word sense