权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Semantic Information Pursuit for Multimodal Data Analysis

多模态数据分析的语义信息追踪

基本信息

批准号：
EP/R018413/1
负责人：
Mark Girolami
金额：
$ 71.84万
依托单位：
Imperial College London
依托单位国家：
英国
项目类别：
Research Grant
财政年份：
2018
资助国家：
英国
起止时间：
2018 至无数据
项目状态：
已结题

来源：
https://gtr.ukri.org/projects?ref=EP%2FR018413%2F1
关键词：
Semantic Information Pursuit Multimodal Data

项目摘要

In 1948, Shannon published his famous paper "A Mathematical Theory of Communication" [88], which laid the foundations of information theory and led to a revolution in communication technologies. Shannon's fundamental contribution was to provide a precise way by which information could be represented,quantified and transmitted. Critical to Shannon's ideas was the notion that the content of a message is irrelevant to its transmission, since any signal can be represented in terms of bits.However, Shannon's theory has some limitations. In 1953, Weaver argued that there are three levelsof communication problems: the technical problem "How accurately can the symbols ofcommunication be transmitted?", the semantic problem "How precisely do the transmitted symbolsconvey the desired meaning?", and the effectiveness problem "How effectively does the receivedmeaning affect conduct in the desired way?" Hence, a key limitation of Shannon's theory is that itis limited to the technical problem. This was also pointed out by Bar-Hillel and Carnap in 1953, who argued that "The Mathematical Theory of Communication, often referred to also as Theory (of Transmission) of Information, as practised nowadays, is not interested in the content of the symbols whose information it measures. The measures, as defined, for instance, by Shannon, have nothing to do with what these symbols symbolise, but only with the frequency of their occurrence." While Bar-Hillel and Carnap argued that "the fundamental concepts of the theory of semantic information can be defined in a straightforward way on the basis of the theory of inductive probability", their work was based primarily on logic rules that were applicable to a very restricted class ofsignals (e.g. text). In the last 60 years there has been extraordinary progress in information theory,signal, image and video processing, statistics, machine learning and optimization, which have ledto dramatic improvements in speech recognition, machine translation, and computer vision technologies.However, the fundamental question of how to represent, quantify and transmit semantic is what this programme of research shall address.

1948年，香农发表了他的著名论文《通信的数学理论》[88]，奠定了信息理论的基础，并导致了通信技术的革命。香农的基本贡献是提供了一种精确的方式，使信息可以被表示、量化和传递。香农的思想的关键是信息的内容与其传输无关，因为任何信号都可以用比特来表示。然而，香农的理论有一些局限性。1953年，韦弗提出了三个层次的通信问题：技术问题“通信符号的传输有多精确？语义问题：“被传递的符号如何准确地传达所期望的意义？””，以及有效性问题“所接收的含义如何有效地以所需的方式影响行为？“因此，香农理论的一个关键局限性是它仅限于技术问题。1953年，巴尔-希勒尔和卡尔纳普也指出了这一点，他们认为：“通信的数学理论，通常也被称为信息理论，就像现在所实践的那样，对它所测量的信息的符号的内容不感兴趣。例如，香农所定义的度量与这些符号所象征的东西无关，而只与它们出现的频率有关。虽然Bar-Hillel和Carnap认为“语义信息理论的基本概念可以在归纳概率理论的基础上以简单的方式定义”，但他们的工作主要基于适用于非常有限的一类信号（例如文本）的逻辑规则。在过去的60年里，信息理论、信号、图像和视频处理、统计学、机器学习和优化等领域取得了巨大的进步，这些进步导致了语音识别、机器翻译和计算机视觉技术的巨大进步。然而，如何表示、量化和传输语义的基本问题是本研究计划所要解决的问题。