2022-02-16: Pyserini: an Information Retrieval Framework
Pyserini is an information retrieval too lkit initially released in 2019 . People can input a query and it will return a list of ranked documents relevant to this query. Pyserini supports sparse retrieval, dense retrieval (involves deep learning), and hybrid retrieval that integrates both approaches. Among those functions, sparse retrieval (BM25 scoring using bag-of-words representations) can serve basic information retrieval purposes. I'd like to introduce sparse retrieval in Pyserini and talk about the installation and use of it in detail. Pyserini depends on Anserini , which is an information retrieval toolkit built on Lucene. Anserini is implemented in JAVA and Pyserini is t he Python wrapper of it . Both of them should be built on JVM and PyJNIus is used to interact with the JVM. Installation of Pyse rini (S parse Retrieval Mode) Pyserini can be installed in an Anaconda virtual environment. I did this in a Windows ...