@inproceedings{b40ca99d439e4172bbbbc8b482e102a6,
title = "mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval",
abstract = "We present systematic efforts in building long-context multilingual text representation model (TRM) and reranker from scratch for text retrieval. We first introduce a text encoder (base size) enhanced with RoPE and unpadding, pretrained in a native 8192-token context (longer than 512 of previous multilingual encoders). Then we construct a hybrid TRM and a cross-encoder reranker by contrastive learning. Evaluations show that our text encoder outperforms the same-sized previous state-of-the-art XLM-R. Meanwhile, our TRM and reranker match the performance of large-sized state-of-the-art BGE-M3 models and achieve better results on long-context retrieval benchmarks. Further analysis demonstrate that our proposed models exhibit higher efficiency during both training and inference. We believe their efficiency and effectiveness could benefit various researches and industrial applications.",
author = "Xin Zhang and Yanzhao Zhang and Dingkun Long and Wen Xie and Ziqi Dai and Jialong Tang and Huan Lin and Baosong Yang and Pengjun Xie and Fei Huang and Meishan Zhang and Wenjie Li and Min Zhang",
note = "Publisher Copyright: {\textcopyright} 2024 Association for Computational Linguistics.; 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, EMNLP 2024 ; Conference date: 12-11-2024 Through 16-11-2024",
year = "2024",
doi = "10.18653/v1/2024.emnlp-industry.103",
language = "英语",
series = "EMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Industry Track",
publisher = "Association for Computational Linguistics (ACL)",
pages = "1393--1412",
editor = "Franck Dernoncourt and Daniel Preotiuc-Pietro and Anastasia Shimorina",
booktitle = "EMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Industry Track",
address = "澳大利亚",
}