cross-encoder-MiniLM-L12-MarginMSE

This model is a cross-encoder based on microsoft/MiniLM-L12-H384-uncased. It was trained on Ms-Marco using loss marginMSE 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 marginMSE

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("microsoft/MiniLM-L12-H384-uncased")
model = AutoModelForSequenceClassification.from_pretrained("xpmir/cross-encoder-MiniLM-L12-MarginMSE")

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	40.11	46.54
trec2019	96.12	73.32
trec2020	94.68	72.91
fever	82.18	81.88
arguana	24.15	35.67
climate_fever	34.63	25.59
dbpedia	76.96	46.80
fiqa	45.41	37.74
hotpotqa	88.85	73.22
nfcorpus	56.46	34.14
nq	53.82	58.82
quora	75.61	78.34
scidocs	28.54	16.00
scifact	67.32	69.70
touche	64.56	33.73
trec_covid	91.95	67.53
robust04	74.56	50.40
lotte_writing	67.52	58.82
lotte_recreation	62.36	56.60
lotte_science	46.95	38.79
lotte_technology	53.93	45.52
lotte_lifestyle	72.17	62.83
Mean In Domain	76.97	64.26
BEIR 13	60.80	50.70
LoTTE (OOD)	62.91	52.16