Gecko: Versatile Text Embeddings Distilled from Large Language Models.
Jinhyuk LeeZhuyun DaiXiaoqi RenBlair ChenDaniel CerJeremy R. ColeKai HuiMichael BoratkoRajvi KapadiaWen DingYi LuanSai Meher Karthik DudduGustavo Hernández ÁbregoWeiqiang ShiNithi GuptaAditya KusupatiPrateek JainSiddhartha Reddy JonnalagaddaMing-Wei ChangIftekhar NaimPublished in: CoRR (2024)
Keyphrases
- language model
- information retrieval
- language modeling
- document level
- document retrieval
- n gram
- language modelling
- retrieval model
- multiword
- speech recognition
- statistical language models
- probabilistic model
- text retrieval
- query expansion
- test collection
- text mining
- translation model
- smoothing methods
- context sensitive
- vector space
- text documents
- document ranking
- language models for information retrieval
- vector space model
- ad hoc information retrieval
- okapi bm
- improve retrieval effectiveness
- language model for information retrieval
- keywords
- retrieval effectiveness
- query terms
- semantic information
- visual features
- low dimensional
- distance measure
- hidden markov models
- search engine