EriBERTa: A Bilingual Pre-Trained Language Model for Clinical Natural Language Processing.
Iker de la IglesiaAitziber AtutxaKoldo GojenolaAnder BarrenaPublished in: CoRR (2023)
Keyphrases
- language model
- pre trained
- natural language processing
- machine translation
- language modeling
- cross lingual
- cross language retrieval
- translation model
- statistical machine translation
- multiword
- training data
- document retrieval
- chinese english
- probabilistic model
- information retrieval
- information extraction
- training examples
- machine learning
- query expansion
- n gram
- natural language
- wordnet
- speech recognition
- retrieval model
- cross language
- context sensitive
- ad hoc information retrieval
- test collection
- cross language information retrieval
- text mining
- control signals
- named entities
- question answering
- semantic relations
- named entity recognition
- query terms
- part of speech
- query translation
- labeled data
- maximum likelihood
- prior knowledge
- image retrieval