Unsupervised Bitext Mining and Translation via Self-trained Contextual Embeddings.
Phillip KeungJulian SalazarYichao LuNoah A. SmithPublished in: Trans. Assoc. Comput. Linguistics (2020)
Keyphrases
- contextual information
- unsupervised learning
- data driven
- text mining
- data mining
- mining algorithm
- frequent patterns
- supervised training
- pattern mining
- sequential patterns
- machine translation
- supervised learning
- itemsets
- information retrieval
- association rule mining
- support vector
- vector space
- active learning
- context sensitive
- training data
- frequent itemsets
- semi supervised
- distance measure
- data mining methods
- data sets
- training process
- cross language information retrieval