Neural Approaches to Multilingual Information Retrieval
Paper • 2209.01335 • Published
How to use eugene-yang/dpr-xlmr-large-mtt-neuclir with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("feature-extraction", model="eugene-yang/dpr-xlmr-large-mtt-neuclir") # Load model directly
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("eugene-yang/dpr-xlmr-large-mtt-neuclir")
model = AutoModel.from_pretrained("eugene-yang/dpr-xlmr-large-mtt-neuclir")DPR model trained for NeuCLIR with MTT with MS-MARCO English queries and translated documents in Chinese, Persian, and Russian.
Translation can be found in neuMARCO on ir-datasets.
Please cite the following paper if you use this model
@inproceedings{ecir2023mlir,
title = {Neural Approaches to Multilingual Information Retrieval},
author = {Dawn Lawrie and Eugene Yang and Douglas W Oard and James Mayfield},
booktitle = {Proceedings of the 45th European Conference on Information Retrieval (ECIR)},
year = {2023},
url = {https://arxiv.org/abs/2209.01335}
}