DRhard
DRhard copied to clipboard
SIGIR'21: Optimizing DR with hard negatives and achieving SOTA first-stage retrieval performance on TREC DL Track.
Thanks for your released beautiful and easy-to-follow code ! It is very helpful to the dense retrieval researchers as me. However, maybe I have met a bug in the preprocess.py....
Hi, jingtao can you share the warmup model for the doc ranking data?
Hi, thank you for publishing the code for your interesting paper. I was just trying to reproduce STAR results in ANCE setup, i.e. I am using static hard negatives and...
Hi, I am trying to understand how you combined the `hard negative loss` Ls with the `in-batch random negative loss` Lr, as in the paper the `in-batch random negative loss`...
There is one line missing at the end of download_data.sh: gunzip docleaderboard-queries.tsv.gz
Hi Jingtao, Thanks for open-source this interesting work and detailed implementation. I have a question for the hard negative generation, is the `mode` should be `train` instead of `dev`? ```...