VictorMorand's picture
Upload README.md with huggingface_hub
20d345a verified
metadata
language: en
license: apache-2.0
library_name: transformers
base_model: bert-base-uncased
model_name: cross-encoder-bert-base-BCE
source: https://github.com/xpmir/cross-encoders
paper: http://arxiv.org/abs/2603.03010
tags:
  - cross-encoder
  - sequence-classification
  - tensorboard
datasets:
  - msmarco
pipeline_tag: text-classification

cross-encoder-bert-base-BCE

Paper All Models GitHub

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.

Contents

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