With More Contexts Comes Better Performance: Contextualized Sense Embeddings for All-Round Word Sense Disambiguation.
Bianca ScarliniTommaso PasiniRoberto NavigliPublished in: EMNLP (1) (2020)
Keyphrases
- word sense disambiguation
- word sense
- ambiguous words
- sense disambiguation
- wordnet
- target word
- natural language processing
- machine translation
- co occurrence
- linguistic knowledge
- semantic similarity
- low dimensional
- semantic relatedness
- part of speech
- wide coverage
- feature set
- feature generation
- unsupervised word sense disambiguation
- lexical knowledge
- vector space
- computational linguistics
- lexical information
- information extraction
- tf idf
- text processing
- semantic relations
- machine learning methods
- semantic information
- world knowledge
- n gram
- semi supervised
- training set
- face recognition
- knowledge base