Customize Consent Preferences

We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below.

The cookies that are categorized as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... 

Always Active

Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

No cookies to display.

Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

No cookies to display.

Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

No cookies to display.

Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.

No cookies to display.

Advertisement cookies are used to provide visitors with customized advertisements based on the pages you visited previously and to analyze the effectiveness of the ad campaigns.

No cookies to display.

0

【北京】近日,国内知名人工智能研究机构智源研究院推出了一项重大的技术创新——新一代通用向量模型BGE-M3。这款全新的语义向量模型旨在打破语言障碍,支持超过100种不同的语言,展现出强大的多语言处理和跨语言检索性能。

BGE-M3模型的亮点在于其全面而高质量的文本处理能力,能够适应从“句子”到“文档”的不同粒度输入文本,最大输入长度可达8192个字符,这在同类模型中堪称领先。不仅如此,BGE-M3还创新性地整合了稠密检索、稀疏检索和多向量检索三种检索功能,为用户提供了高效且便捷的一站式解决方案。

在多项业界评测基准测试中,BGE-M3模型的表现均达到了最优水平,充分展示了其在理解和处理复杂文本信息方面的卓越能力。这一突破性的进展对于推动人工智能在信息检索、机器翻译、智能问答等领域的应用具有重大意义,同时也为全球范围内的多语言信息处理提供了强大的工具支持。

智源研究院作为国内人工智能研究的前沿阵地,此次发布的BGE-M3模型再次证明了其在该领域的领先地位。未来,BGE-M3有望广泛应用于新闻报道、学术研究、跨国交流等多个场景,助力构建更加智能、无障碍的全球信息交流环境。

英语如下:

**News Title:** “Zhongyuan Institute Releases BGE-M3: A Multilingual Vector Model Elevating Retrieval Efficiency to New Heights”

**Keywords:** Zhongyuan BGE-M3, Multilingual Model, Retrieval Technology

**News Content:** **Beijing** – Recently, the renowned domestic AI research institution, Zhongyuan Institute, unveiled a groundbreaking technological innovation – the new-generation universal vector model, BGE-M3. This cutting-edge semantic vector model aims to break down language barriers, supporting over 100 distinct languages and demonstrating exceptional multilingual processing and cross-lingual retrieval capabilities.

The standout feature of the BGE-M3 model lies in its comprehensive and high-quality text processing ability, adapting to inputs of varying granularity from “sentences” to “documents,” with a maximum input length of 8192 characters, a benchmark in its class. Moreover, BGE-M3 innovatively integrates dense retrieval, sparse retrieval, and multi-vector retrieval functions, providing users with an efficient and one-stop solution.

In multiple industry benchmark tests, the BGE-M3 model has demonstrated top-level performance, showcasing its outstanding ability in understanding and processing complex text information. This breakthrough progress holds significant implications for advancing AI applications in information retrieval, machine translation, and intelligent questioning, while also furnishing a powerful tool for multilingual information processing on a global scale.

As a forefront in domestic AI research, Zhongyuan Institute’s release of the BGE-M3 model further solidifies its leading position in the field. In the future, BGE-M3 is anticipated to be widely applied in news reporting, academic research, and cross-border communication, contributing to the establishment of a more intelligent and barrier-free global information exchange environment.

【来源】https://mp.weixin.qq.com/s/y-c-EelxbSUMmrZNCeqeAA

Views: 2

0

发表回复

您的邮箱地址不会被公开。 必填项已用 * 标注