GitHub / jingtaozhan / RepBERT-Index
RepBERT is a competitive first-stage retrieval technique. It represents documents and queries with fixed-length contextualized embeddings. The inner products of them are regarded as relevance scores. Its efficiency is comparable to bag-of-words methods.
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jingtaozhan%2FRepBERT-Index
PURL: pkg:github/jingtaozhan/RepBERT-Index
Stars: 62
Forks: 10
Open issues: 1
License: bsd-3-clause
Language: Python
Size: 36.1 KB
Dependencies parsed at: Pending
Created at: about 5 years ago
Updated at: over 2 years ago
Pushed at: almost 4 years ago
Last synced at: over 2 years ago
Topics: information-retrieval, pytorch, web-search