Synthetic, yet natural: Properties of WordNet random walk corpora and the impact of rare words on embedding performance.
Filip KlubickaAlfredo MaldonadoAbhijit MahalunkarJohn D. KelleherPublished in: GWC (2019)
Keyphrases
- random walk
- wordnet
- lexical resources
- word sense disambiguation
- natural language processing
- lexical database
- text documents
- semantic distance
- lexical knowledge
- keywords
- word similarity
- chinese english
- semantic relatedness
- co occurrence
- word sense
- semantic information
- semantic relations
- markov chain
- semantic similarity
- linguistic knowledge
- lexical information
- knowledge base
- sense disambiguation
- markov random walk
- semantic features
- link prediction
- information extraction
- text corpora
- text mining
- semantically related
- parallel corpus
- opinion mining
- vector space
- lexical chains
- named entity recognition
- artificial intelligence