Pomona at SemEval-2016 Task 11: Predicting Word Complexity Based on Corpus Frequency.
David KauchakPublished in: SemEval@NAACL-HLT (2016)
Keyphrases
- word sense disambiguation
- word sense
- word frequencies
- sentence level
- word pairs
- co occurrence
- text corpus
- computational complexity
- worst case
- sense disambiguation
- english words
- multiword
- training corpus
- statistical machine translation
- natural language text
- noun phrases
- sentiment analysis
- n gram
- linguistic information
- word level
- unknown words
- lexical features
- wordnet
- natural language processing