Skip to main navigation Skip to search Skip to main content

mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval

  • Xin Zhang
  • , Yanzhao Zhang
  • , Dingkun Long
  • , Wen Xie
  • , Ziqi Dai
  • , Jialong Tang
  • , Huan Lin
  • , Baosong Yang
  • , Pengjun Xie
  • , Fei Huang
  • , Meishan Zhang*
  • , Wenjie Li
  • , Min Zhang
  • *Corresponding author for this work
  • Alibaba Group Holding Ltd.
  • Hong Kong Polytechnic University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.

Original languageEnglish
Title of host publicationEMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Industry Track
EditorsFranck Dernoncourt, Daniel Preotiuc-Pietro, Anastasia Shimorina
PublisherAssociation for Computational Linguistics (ACL)
Pages1393-1412
Number of pages20
ISBN (Electronic)9798891761667
DOIs
StatePublished - 2024
Externally publishedYes
Event2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, EMNLP 2024 - Miami, United States
Duration: 12 Nov 202416 Nov 2024

Publication series

NameEMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Industry Track

Conference

Conference2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, EMNLP 2024
Country/TerritoryUnited States
CityMiami
Period12/11/2416/11/24

Fingerprint

Dive into the research topics of 'mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval'. Together they form a unique fingerprint.

Cite this