arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.03470cs.CL
收藏

Wikipedia概念和实体的向量嵌入

Vector Embedding of Wikipedia Concepts and Entities

Dalhousie University(达尔豪斯大学)

Ehsan Sherkat, Evangelos Milios

摘要:

将深度学习用于不同的机器学习任务,例如图像分类和词嵌入,最近受到了很多关注。与其他方法相比,其在特定自然语言处理(NLP)任务中报告的吸引人的性能是其受欢迎的原因。词嵌入是将词或短语映射到低维数值向量的任务。在本文中,我们使用深度学习来嵌入维基百科的概念和实体。维基百科的英文版包含超过500万页,这表明它有能力涵盖许多英语实体,短语和概念。维基百科的每一页都被视为一个概念。有些概念对应于实体,如人名、组织或地点。与词嵌入相反,维基百科概念嵌入并不模糊,因此对于表面形式相似但提及不同的概念有不同的向量。我们提出了几种方法,并评估其性能的基础上概念类比和概念相似性任务。结果表明,所提出的方法具有相当的性能,在某些情况下,甚至高于国家的最先进的方法。

英文摘要:

Using deep learning for different machine learning tasks such as image classification and word embedding has recently gained many attentions. Its appealing performance reported across specific Natural Language Processing (NLP) tasks in comparison with other approaches is the reason for its popularity. Word embedding is the task of mapping words or phrases to a low dimensional numerical vector. In this paper, we use deep learning to embed Wikipedia Concepts and Entities. The English version of Wikipedia contains more than five million pages, which suggest its capability to cover many English Entities, Phrases, and Concepts. Each Wikipedia page is considered as a concept. Some concepts correspond to entities, such as a person's name, an organization or a place. Contrary to word embedding, Wikipedia Concepts Embedding is not ambiguous, so there are different vectors for concepts with similar surface form but different mentions. We proposed several approaches and evaluated their performance based on Concept Analogy and Concept Similarity tasks. The results show that proposed approaches have the performance comparable and in some cases even higher than the state-of-the-art methods.

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。

↑