Multi-domain Cross-lingual Information Extraction from Clean and Noisy Texts.
Horacio SaggionSandra SzaszPublished in: STIL (2011)
Keyphrases
- multi domain
- cross lingual
- information extraction
- machine translation
- text documents
- event extraction
- word sense
- cross domain
- natural language
- natural language processing
- text mining
- domain specific
- cross lingual information retrieval
- document clustering
- language modeling
- news articles
- text classification
- named entity recognition
- transfer learning
- open domain
- named entities
- web documents
- word sense disambiguation
- information retrieval
- machine learning
- translation model
- question answering
- feature selection
- heterogeneous networks
- statistical machine translation
- search engine
- probabilistic model
- language model