BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels.
Yimin JingDeyi XiongYan ZhenPublished in: EMNLP/IJCNLP (1) (2019)
Keyphrases
- cross lingual
- reading comprehension
- machine translation
- cross lingual information retrieval
- cross language
- computer assisted
- language independent
- language modeling
- parallel corpus
- multi lingual
- parallel corpora
- text classification
- multiple choice
- transfer learning
- language specific
- probabilistic model
- machine translation system
- word alignment
- query translation
- word segmentation
- translation model
- clustering algorithm
- document clustering
- indian languages
- bayesian networks