MultiSeg: Parallel Data and Subword Information for Learning Bilingual Embeddings in Low Resource Scenarios.
Efsun Sarioglu KayiVishal AnandSmaranda MuresanPublished in: SLTU/CCURL@LREC (2020)
Keyphrases
- prior knowledge
- information resources
- raw data
- data sets
- background knowledge
- collected data
- information sources
- historical data
- complex data
- data collection
- sensitive information
- learning algorithm
- data sources
- sensor data
- log data
- computer systems
- previously learned
- domain experts
- sensory data
- critical information
- supervised learning
- information extraction
- domain knowledge
- training data
- learning scenarios
- end users
- learning process
- data mining