Construction of a Benchmark Data Set for Cross-lingual Word Sense Disambiguation.
Els LefeverVéronique HostePublished in: LREC (2010)
Keyphrases
- cross lingual
- word sense disambiguation
- machine translation
- word sense
- data sets
- language independent
- natural language processing
- cross language
- information extraction
- language modeling
- parallel corpus
- wordnet
- translation model
- cross language information retrieval
- training data
- target language
- text classification
- query translation
- natural language
- statistical machine translation
- parallel corpora
- data mining
- expert systems
- feature vectors
- feature set
- knowledge base
- document clustering
- machine translation system