Cross-Lingual Adaptation of Broadcast Transcription System to Polish Language Using Public Data Sources.
Jan NouzaPetr CervaRadek SafaríkPublished in: LTC (2015)
Keyphrases
- cross lingual
- data sources
- parallel corpus
- european languages
- language specific
- monolingual and cross lingual
- indian languages
- machine translation
- language independent
- cross lingual information retrieval
- linguistic resources
- language modeling
- source language
- cross language
- comparable corpora
- event extraction
- machine translation system
- word alignment
- target language
- data sets
- translation model
- natural language
- bilingual dictionaries
- query translation
- text classification
- parallel corpora
- word segmentation
- news articles
- document clustering
- transfer learning
- probabilistic model
- databases
- language model
- database systems
- information retrieval
- data mining
- monolingual retrieval