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 2106.15047cs.AI
收藏

基准测试知识驱动的零样本学习

Benchmarking Knowledge-driven Zero-shot Learning

Zhejiang University(浙江大学);University of Oxford(牛津大学);The University of Edinburgh(爱丁堡大学);Huawei Technologies Co., Ltd.(华为技术有限公司)

Yuxia Geng, Jiaoyan Chen, Xiang Zhuang, Zhuo Chen, Jeff Z. Pan, Juan Li, Zonggang Yuan, Huajun Chen

摘要:

外部知识(又名边信息)在零样本学习(ZNL)中起着关键作用,ZNL的目的是用从未出现在训练数据中的不可见类进行预测。文本、属性等几种外部知识已被广泛研究,但它们本身的语义不完备。因此,最近的一些研究建议使用知识图谱(KG),由于其高表达性和兼容性,用于表示各种知识。然而,学习型语言社区仍然缺乏标准的基准来研究和比较不同的外部知识设置和不同的基于知识生成的学习型语言方法。在本文中,我们提出了涵盖三项任务的六种资源,即,zero-shot图像分类(ZH-IMGC)、zero-shot关系抽取(ZH-RE)和zero-shot KG完成(ZH-KGC)。每个资源都有一个标准的XML基准和一个KG,KG包含从文本到属性、从关系知识到逻辑表达式的语义。我们已经清楚地介绍了这些资源,包括它们的结构、统计数据、数据格式和使用案例。不同的方法。更重要的是,我们进行了全面的基准研究,采用了两种通用和最先进的方法,两种特定于环境的方法和一种可解释的方法。我们讨论和比较了不同的CNOL范式w.r.t.不同的外部知识设置,并发现我们的资源有很大的潜力,开发更先进的机器学习方法和更多的解决方案,应用KG增强机器学习。所有的资源都可以在https://github.com/China-UK-ZSL/Resources_for_KZSL上找到。

英文摘要:

External knowledge (a.k.a. side information) plays a critical role in zero-shot learning (ZSL) which aims to predict with unseen classes that have never appeared in training data. Several kinds of external knowledge, such as text and attribute, have been widely investigated, but they alone are limited with incomplete semantics. Some very recent studies thus propose to use Knowledge Graph (KG) due to its high expressivity and compatibility for representing kinds of knowledge. However, the ZSL community is still in short of standard benchmarks for studying and comparing different external knowledge settings and different KG-based ZSL methods. In this paper, we proposed six resources covering three tasks, i.e., zero-shot image classification (ZS-IMGC), zero-shot relation extraction (ZS-RE), and zero-shot KG completion (ZS-KGC). Each resource has a normal ZSL benchmark and a KG containing semantics ranging from text to attribute, from relational knowledge to logical expressions. We have clearly presented these resources including their construction, statistics, data formats and usage cases w.r.t. different ZSL methods. More importantly, we have conducted a comprehensive benchmarking study, with two general and state-of-the-art methods, two setting-specific methods and one interpretable method. We discussed and compared different ZSL paradigms w.r.t. different external knowledge settings, and found that our resources have great potential for developing more advanced ZSL methods and more solutions for applying KGs for augmenting machine learning. All the resources are available at https://github.com/China-UK-ZSL/Resources_for_KZSL.

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。

↑