Language-agnostic Representation from Multilingual Sentence Encoders for Cross-lingual Similarity Estimation.
Nattapong TiyajamornTomoyuki KajiwaraYuki AraseMakoto OnizukaPublished in: EMNLP (1) (2021)
Keyphrases
- cross lingual
- parallel corpus
- machine translation
- language specific
- monolingual and cross lingual
- target language
- source language
- language independent
- cross language
- cross lingual information retrieval
- language modeling
- natural language
- similarity estimation
- indian languages
- machine translation system
- query translation
- cross language information retrieval
- word alignment
- text classification
- linguistic resources
- statistical machine translation
- news articles
- retrieval model
- transfer learning
- comparable corpora
- information retrieval
- probabilistic model
- information extraction
- parallel corpora
- translation model
- document clustering