Skip to content

Latest commit

 

History

History
19 lines (13 loc) · 1005 Bytes

README.md

File metadata and controls

19 lines (13 loc) · 1005 Bytes

Information Retrieval

Indexes

Converting ms-marco.trec.gz to lucene index:

python -m pyserini.index -collection CleanTrecCollection -generator DefaultLuceneDocumentGenerator -threads 1 -input C:/msmarco-docs.trec -index C:/msmarco-doc/lucene-index.msmarco-doc.pos+docvectors+rawdocs -storePositions -storeDocvectors -storeRaw

where -input specifies the folder with the file ms-marco.trec.gz and -index specifies the output folder. Pyserini needs to be installed.

Evaluation

To use trec_eval.exe, cygwin must be installed and C:/cygwin64/bin must be added to the system and environment PATH variable.

Links