Hyperpolyglot LLMs: Cross-Lingual Interpretability in Token Embeddings.
Andrea W. Wen-YiDavid MimnoPublished in: EMNLP (2023)
Keyphrases
- cross lingual
- machine translation
- cross lingual information retrieval
- language modeling
- language independent
- vector space
- cross language
- event extraction
- low dimensional
- text classification
- parallel corpus
- translation model
- document clustering
- language model
- transfer learning
- dimensionality reduction
- mono lingual
- parallel corpora
- information retrieval
- natural language
- indian languages
- news articles
- query translation
- natural language processing
- bayesian networks
- search engine