Tuned and GPU-Accelerated Parallel Data Mining from Comparable Corpora.
Krzysztof WolkKrzysztof MarasekPublished in: TSD (2015)
Keyphrases
- gpu accelerated
- parallel data mining
- comparable corpora
- cross language information retrieval
- parallel corpora
- news articles
- data mining
- finite element
- bilingual lexicon
- machine translation
- language modeling
- text corpora
- real time
- word pairs
- text documents
- cross lingual
- neural network
- sequence alignment
- cross language
- query translation
- bi directional
- translation model
- latent semantic analysis
- linguistic resources
- text retrieval
- machine learning