Prompt-Tuning Can Be Much Better Than Fine-Tuning on Cross-lingual Understanding With Multilingual Language Models.
Lifu TuCaiming XiongYingbo ZhouPublished in: EMNLP (Findings) (2022)
Keyphrases
- cross lingual
- fine tuning
- language modeling
- language model
- cross lingual information retrieval
- language independent
- n gram
- retrieval model
- cross language
- probabilistic model
- query expansion
- pseudo feedback
- parallel corpus
- information retrieval
- document retrieval
- translation model
- test collection
- machine translation
- pseudo relevance feedback
- smoothing methods
- vector space model
- context sensitive
- relevance model
- statistical machine translation
- parallel corpora
- machine learning
- language modeling framework
- out of vocabulary
- linguistic resources
- generative model