arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2212.03533cs.CLcs.IR
收藏

基于弱监督对比预训练的文本嵌入

Text Embeddings by Weakly-Supervised Contrastive Pre-training

Microsoft Corporation(微软公司)

Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei

AI总结:

本文提出基于弱监督对比预训练的文本嵌入模型E5,利用大规模文本对数据集CCPairs训练,在零样本和微调场景下于BEIR和MTEB基准上取得领先性能。

摘要:

本文提出了E5,这是一系列最先进的文本嵌入模型,能够很好地迁移到广泛的任务中。该模型以对比方式进行训练,弱监督信号来自我们构建的大规模文本对数据集(称为CCPairs)。E5可以直接用作通用嵌入模型,适用于任何需要文本单向量表示的任务,如检索、聚类和分类,在零样本和微调设置下均取得了强大的性能。我们在BEIR和MTEB基准的56个数据集上进行了广泛评估。在零样本设置下,E5是第一个在不使用任何标注数据的情况下,在BEIR检索基准上超越强BM25基线的模型。经过微调后,E5在MTEB基准上取得了最佳结果,击败了参数量多40倍的现有嵌入模型。

英文摘要:

This paper presents E5, a family of state-of-the-art text embeddings that transfer well to a wide range of tasks. The model is trained in a contrastive manner with weak supervision signals from our curated large-scale text pair dataset (called CCPairs). E5 can be readily used as a general-purpose embedding model for any tasks requiring a single-vector representation of texts such as retrieval, clustering, and classification, achieving strong performance in both zero-shot and fine-tuned settings. We conduct extensive evaluations on 56 datasets from the BEIR and MTEB benchmarks. For zero-shot settings, E5 is the first model that outperforms the strong BM25 baseline on the BEIR retrieval benchmark without using any labeled data. When fine-tuned, E5 obtains the best results on the MTEB benchmark, beating existing embedding models with 40x more parameters.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑