An Alignment-Based Approach to Semi-Supervised Bilingual Lexicon Induction with Small Parallel Corpora.
Kelly MarchisioPhilipp KoehnConghao XiongPublished in: MTSummit (1) (2021)
Keyphrases
- bilingual lexicon
- parallel corpora
- comparable corpora
- semi supervised
- machine translation
- cross language information retrieval
- cross language
- cross lingual
- labor intensive
- word alignment
- language independent
- machine translation system
- semi supervised learning
- news articles
- word pairs
- sentence level
- active learning
- text corpora
- statistical machine translation
- query translation
- bilingual dictionaries
- labeled data
- unlabeled data
- error prone
- fully automated
- parallel corpus
- language modeling