๐ญ My research lies in Information Retrieval and Web Search. I currently focus on Dense Retrieval with a wide interest in improving its effectiveness, efficiency, and interpretability. The publications are available at my homepage.
Thanks for this interesting work and making the code available. I am Buruo, an MSc student at the University of Glasgow, studying with @cmacdonald. Iโm trying to make a PyTerrier plugin for JPQ.
I am using your pre-built indices, but my evaluation doesn't match those reported in the paper. My best NDCG@10 is 0.5568 on the TREC 2019 Deep Learning track Passage Task.
For us to debug our integration, would you be able to provide results files - i.e. rankings generated by JPQ. This would also be useful for others wishing to compare the JPQ results in their own papers.
hi, jingtaozhan,I am glad to read your paper.However,I don't find the code of PQ Centroid Optimization in the paper.Maybe I misunderstood your paper or code.
Hello developers,
Could you share the code to run the experiments on the ColBERT-V2 model, as in the paper "Joint Optimization of Multi-vector Representation with Product Quantization"?
Thanks for your evaluation code for BEIR repository, it certainly helped me a lot.
I have an additional request, I wish to train the JPQ (and RepCONC if possible) model on a custom dataset from the BEIR repository, which contains pairwise question-passage training pairs.
Can this already be done through the repository? Is there a sample code that I can easily refer to?