Uniformisation de corpus anglais annotés en sens (Unification of sense annotated English corpora for word sense disambiguation).
Loïc VialBenjamin LecouteuxDidier SchwabPublished in: TALN (3) (2017)
Keyphrases
- word sense disambiguation
- word sense
- wide coverage
- sense disambiguation
- natural language processing
- annotated corpus
- wordnet
- hand crafted
- lexical knowledge
- machine translation
- target word
- highly ambiguous
- information extraction
- co occurrence
- unknown words
- cross lingual
- named entity recognition
- named entities
- statistical machine translation
- manually annotated
- semantic similarity
- semantic role labeling
- lexical resources
- relation extraction
- natural language
- ambiguous words
- linguistic knowledge
- semantic relatedness
- parallel corpus
- part of speech
- unsupervised word sense disambiguation
- parallel corpora
- text processing
- training corpus
- semantic roles
- linguistic features
- pos tagging
- artificial intelligence
- information retrieval
- text collections
- semantic features
- machine learning methods
- structured data
- feature set
- feature space