Diacritization as a Machine Translation and as a Sequence Labeling Problem.
Tim SchlippeThuyLinh NguyenStephan VogelPublished in: AMTA (Student Research Workshop) (2008)
Keyphrases
- machine translation
- sequence labeling
- conditional random fields
- named entity recognition
- information extraction
- natural language processing
- dependency parsing
- structured prediction
- cross lingual
- target language
- statistical machine translation
- natural language
- text summarization
- crf model
- named entities
- wordnet
- machine translation system
- cross language information retrieval
- information retrieval
- latent variables
- maximum entropy
- training data
- markov random field
- co occurrence
- knowledge representation
- active learning
- pairwise