arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1608.00841cs.CL
收藏

词义和概念的语义表征

Semantic Representations of Word Senses and Concepts

Sapienza University of Rome(罗马大学);University of Cambridge(剑桥大学)

José Camacho-Collados, Ignacio Iacobacci, Roberto Navigli, Mohammad Taher Pilehvar

摘要:

以机器可解释的形式表示语言项的语义一直是自然语言处理的主要目标。在众多的语言项目中,词汇是最受关注的研究对象。然而,单词表示有一个重要的限制:它们将单词的不同含义合并到一个向量中。词义的表征有可能克服这种固有的局限性。事实上,个别词义和概念的表示最近越来越受欢迎,几个实验结果表明,在从单词级别移动到更深的意义和概念级别时,可以在不同的NLP应用程序中实现相当大的性能改进。关于概念和词义的表示的另一个有趣的点是,这些模型可以无缝地应用于其他语言项目,如单词,短语和句子。

英文摘要:

Representing the semantics of linguistic items in a machine-interpretable form has been a major goal of Natural Language Processing since its earliest days. Among the range of different linguistic items, words have attracted the most research attention. However, word representations have an important limitation: they conflate different meanings of a word into a single vector. Representations of word senses have the potential to overcome this inherent limitation. Indeed, the representation of individual word senses and concepts has recently gained in popularity with several experimental results showing that a considerable performance improvement can be achieved across different NLP applications upon moving from word level to the deeper sense and concept levels. Another interesting point regarding the representation of concepts and word senses is that these models can be seamlessly applied to other linguistic items, such as words, phrases and sentences.

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。

↑