monoBERT trained on MS-Marco

Passage Re-ranking with BERT (Rodrigo Nogueira, Kyunghyun Cho). 2019. https://arxiv.org/abs/1901.04085

This model has been trained on MsMarco v1

Using the model

The model can be loaded with experimaestro IR

from xpmir.models import AutoModel

# Model that can be re-used in experiments
model, init_tasks = AutoModel.load_from_hf_hub("xpmir/monobert")

# Use this if you want to actually use the model
model = AutoModel.load_from_hf_hub("xpmir/monobert", as_instance=True)
model.rsv("walgreens store sales average", "The average Walgreens salary ranges...")

Results

Dataset	AP	P@20	RR	RR@10	Success@5	nDCG	nDCG@10	nDCG@20
msmarco_dev	0.3722	0.0377	0.3774	0.3689	0.5390	0.4767	0.4316	0.4517
trec2019	0.4900	0.7512	0.9426	0.9426	1.0000	0.6933	0.7190	0.6997
trec2020	0.4851	0.6269	0.9354	0.9354	0.9815	0.6935	0.7156	0.6796