cross-encoder-ettin-32m-BCE

This model is a cross-encoder based on jhu-clsp/ettin-encoder-32m. 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
• 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("xpmir/cross-encoder-ettin-32m-BCE")
model = AutoModelForSequenceClassification.from_pretrained("xpmir/cross-encoder-ettin-32m-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	29.02	34.90
trec2019	82.89	57.70
trec2020	83.38	54.29
fever	63.46	65.87
arguana	10.93	16.36
climate_fever	11.76	8.53
dbpedia	50.23	25.98
fiqa	34.99	27.92
hotpotqa	74.14	56.75
nfcorpus	36.28	18.36
nq	35.17	40.86
quora	68.46	69.29
scidocs	19.36	10.42
scifact	53.97	55.59
touche	55.39	28.45
trec_covid	77.66	56.06
robust04	39.31	21.96
lotte_writing	50.73	44.07
lotte_recreation	46.97	43.00
lotte_science	28.21	25.25
lotte_technology	36.75	31.49
lotte_lifestyle	58.57	51.37
Mean In Domain	65.10	48.96
BEIR 13	45.52	36.96
LoTTE (OOD)	43.42	36.19