BeIR/query-gen-msmarco-t5-base-v1

The T5-base model was trained on the MS MARCO Passage Dataset, which consists of about 500k real search queries from Bing together with the relevant passage . The model can be used for query generation to learn semantic search models without requiring annotated training data: Synthetic Query Generation. The model is the t5-Base model from docTTTTTquery. It can also be used in the search engine's search engine for semantic queries without annotating training data. The query generation tool is called Synthetic Queries. It is based on the T5ForConditionalGeneration. It has been used for queries in the past for the first time in a search engine.,