Dense Information Retrieval on a Latin Digital Library via LaBSE and LatinBERT Embeddings.
Federico A. GalatoloGabriele MartinoMario G. C. A. CiminoChiara Ombretta TommasiPublished in: DATA (2023)
Keyphrases
- digital libraries
- information retrieval
- information access
- effective retrieval
- question answering
- document collections
- information extraction
- vector space
- learning to rank
- document search
- information retrieval systems
- multi lingual
- search engine
- language model
- stereo correspondence
- document retrieval
- sci tech
- computational linguistics
- query expansion
- low dimensional
- metadata
- language modeling
- cultural heritage
- vector space model
- tf idf
- test collection
- digital documents
- machine learning
- bibliographic information
- database