cross-encoder-bert-base-ADR-MSE

This model is a cross-encoder based on bert-base-uncased. It was trained on Ms-Marco using loss ADR as part of a reproducibility paper for training cross encoders: "Reproducing and Comparing Distillation Techniques for Cross-Encoders", see the paper for more details.

Model Description
Usage
Evals

Model Description

This model is intended for re-ranking the top results returned by a retrieval system (like BM25, Bi-Encoders or SPLADE).

Training Data: MS MARCO Passage
Language: English
Loss ADR

Training can be easily reproduced using the assiciated repository. The exact training configuration used for this model is also detailed in config.yaml.

Usage

Quick Start:

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
model = AutoModelForSequenceClassification.from_pretrained("xpmir/cross-encoder-bert-base-ADR-MSE")

features = tokenizer("What is experimaestro ?", "Experimaestro is a powerful framework for ML experiments management...", padding=True, truncation=True, return_tensors="pt")

model.eval()
with torch.no_grad():
    scores = model(**features).logits
    print(scores)

Evaluations

We provide evaluations of this cross-encoder re-ranking the top 1000 documents retrieved by naver/splade-v3-distilbert.

dataset	RR@10	nDCG@10
msmarco_dev	36.50	42.98
trec2019	97.29	74.07
trec2020	92.87	71.74
fever	81.06	81.04
arguana	23.00	34.49
climate_fever	27.78	20.52
dbpedia	76.55	46.14
fiqa	42.55	34.79
hotpotqa	90.03	73.39
nfcorpus	55.59	34.20
nq	53.32	58.11
quora	80.84	82.20
scidocs	28.26	15.66
scifact	66.07	69.12
touche	62.66	33.81
trec_covid	84.83	65.90
robust04	70.37	48.02
lotte_writing	65.26	56.58
lotte_recreation	58.83	53.28
lotte_science	43.66	36.67
lotte_technology	50.56	42.04
lotte_lifestyle	68.66	59.78
Mean In Domain	75.55	62.93
BEIR 13	59.43	49.95
LoTTE (OOD)	59.56	49.39