Measuring Lexical Diversity in Texts: The Twofold Length Problem.
Yves BestgenPublished in: CoRR (2023)
Keyphrases
- linguistic information
- natural language text
- linguistic analysis
- keywords
- wordnet
- natural language
- word sense
- context sensitive
- domain specific
- semantic relatedness between words
- linguistic features
- semantic relations
- knowledge resources
- genetic algorithm
- total length
- lexical information
- lexical features
- legal texts
- syntactic categories
- semantic network
- natural language processing
- classifier ensemble
- automatically generated
- text documents
- co occurrence