Negar Arabzadeh

reproducing your results on MS MARCO

8

Hi, Thank you for your great work! I am willing to replicate your results on MS MARCO passage collection and I have a question regarding `Luyu/co-condenser-marco` model. Is this the...

Hi, I was able to replicate the MRR@10 that you reported in the paper ( 0.38) but I was wondering what is the difference between the number that is reported...

In https://github.com/texttron/tevatron/tree/main/examples/coCondenser-marco#index-search `python ../msmarco-passage-ranking/score_to_marco.py rank.txt` should be replaced with `python ../msmarco-passage-ranking/score_to_marco.py rank.tsv`

nonzero elements are always in same dimensions

6

I applied SPINE on top of some embedding and I got sparse embeddings but nonzero elements are exactly in the same dimensions always in almost all the samples. I attached...

example of input dataframe

3

Thank you for the great work. Can you please bring one example of the inputs? i.e., what should be the data frame look like? more specifically what is caption_col_name ?...

bug in OnFields expanders

1

There is a bug in AdapOnFields and OnFields expanders that sometimes it converts characters Unicode to query term weights. This happens rarely. However, it should be fixed in future versions.