cross-encoder-bert-base-BCE

This model is a cross-encoder based on bert-base-uncased. It was trained on Ms-Marco using loss bce 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 bce

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-BCE")

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	37.63	44.00
trec2019	90.00	67.38
trec2020	91.96	68.39
fever	76.49	77.27
arguana	21.41	32.09
climate_fever	33.26	24.32
dbpedia	71.92	41.65
fiqa	42.57	34.34
hotpotqa	86.45	70.63
nfcorpus	49.72	27.88
nq	51.49	56.28
quora	71.56	74.43
scidocs	24.84	13.74
scifact	63.67	66.02
touche	61.83	32.49
trec_covid	84.43	58.66
robust04	66.34	42.61
lotte_writing	66.37	57.13
lotte_recreation	57.83	52.25
lotte_science	41.88	35.02
lotte_technology	50.35	41.56
lotte_lifestyle	68.01	58.36
Mean In Domain	73.20	59.92
BEIR 13	56.90	46.91
LoTTE (OOD)	58.46	47.82