SPLADE-v3: New baselines for SPLADE
Paper • 2403.06789 • Published • 5
How to use nirantk/splade-v3-lexical with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("fill-mask", model="nirantk/splade-v3-lexical") # Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("nirantk/splade-v3-lexical")
model = AutoModelForMaskedLM.from_pretrained("nirantk/splade-v3-lexical")SPLADE-v3-Lexical is the SPLADE-Lexical version of naver/splade-v3 (no expansion on the query side - only term weighting).
For more details, see our arXiv companion book: https://arxiv.org/abs/2403.06789
To use SPLADE, please visit our GitHub repository: https://github.com/naver/splade
| MRR@10 (MS MARCO dev) | avg nDCG@10 (BEIR-13) | |
|---|---|---|
naver/splade-v3-lexical |
40.0 | 49.1 |
If you use our checkpoint, please cite our work:
@misc{lassance2024spladev3,
title={SPLADE-v3: New baselines for SPLADE},
author={Carlos Lassance and Hervé Déjean and Thibault Formal and Stéphane Clinchant},
year={2024},
eprint={2403.06789},
archivePrefix={arXiv},
primaryClass={cs.IR},
copyright = {Creative Commons Attribution Non Commercial Share Alike 4.0 International}
}