mPLM-Sim: Better Cross-Lingual Similarity and Transfer in Multilingual Pretrained Language Models.
Peiqin LinChengzhi HuZheyu ZhangAndré F. T. MartinsHinrich SchützePublished in: EACL (Findings) (2024)
Keyphrases
- cross lingual
- language modeling
- language model
- cross lingual information retrieval
- n gram
- language independent
- pseudo feedback
- translation model
- cross language
- information retrieval
- document retrieval
- retrieval model
- probabilistic model
- query expansion
- parallel corpus
- test collection
- transfer learning
- machine translation
- similarity measure
- context sensitive
- semantic similarity
- text classification
- vector space model
- query terms
- statistical machine translation
- parallel corpora
- out of vocabulary
- cross language retrieval
- query translation
- pseudo relevance feedback
- question answering
- linguistic resources
- digital libraries
- bayesian networks
- language modeling framework