CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1, 500+ Language Pairs.
Abhik BhattacharjeeTahmid HasanWasi Uddin AhmadYuan-Fang LiYong-Bin KangRifat ShahriyarPublished in: ACL (1) (2023)
Keyphrases
- cross lingual
- parallel corpus
- language specific
- european languages
- machine translation
- indian languages
- source language
- cross language
- target language
- machine translation system
- language independent
- language modeling
- comparable corpora
- cross lingual information retrieval
- mono lingual
- natural language
- linguistic resources
- event extraction
- bilingual dictionaries
- text classification
- statistical machine translation
- query translation
- word alignment
- news articles
- document clustering
- monolingual retrieval
- parallel corpora
- pairwise
- character n grams
- word sense
- translation model
- transfer learning
- natural language processing
- active learning
- search engine
- word pairs
- out of vocabulary
- machine learning
- text categorization
- language model
- artificial intelligence