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 2006.09896cs.CLcs.AIcs.LG
收藏

概念的可学习性及其在比较词嵌入算法中的应用

On the Learnability of Concepts: With Applications to Comparing Word Embedding Algorithms

University of Bristol(布里斯托尔大学)

Adam Sutton, Nello Cristianini

摘要:

词嵌入在多个自然语言处理(NLP)应用中被广泛使用。它们是与字典中的每个单词相关联的坐标,从大型语料库中这些单词的统计特性推断出来。在本文中,我们介绍了“概念”的概念,作为一个列表的话,共享语义内容。我们使用这个概念来分析某些概念的可学习性,定义为分类器在训练一个概念的随机子集后识别概念中不可见成员的能力。我们首先使用这种方法来测量预训练词嵌入上概念的可学习性。然后,我们开发了一个统计分析的概念的可学习性,假设检验和ROC曲线的基础上,为了比较使用一个固定的语料库和超参数的各种嵌入算法的相对优点。我们发现,所有的嵌入方法捕捉这些单词列表的语义内容,但fastText的表现优于其他。

英文摘要:

Word Embeddings are used widely in multiple Natural Language Processing (NLP) applications. They are coordinates associated with each word in a dictionary, inferred from statistical properties of these words in a large corpus. In this paper we introduce the notion of "concept" as a list of words that have shared semantic content. We use this notion to analyse the learnability of certain concepts, defined as the capability of a classifier to recognise unseen members of a concept after training on a random subset of it. We first use this method to measure the learnability of concepts on pretrained word embeddings. We then develop a statistical analysis of concept learnability, based on hypothesis testing and ROC curves, in order to compare the relative merits of various embedding algorithms using a fixed corpora and hyper parameters. We find that all embedding methods capture the semantic content of those word lists, but fastText performs better than the others.

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。

↑