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 1608.07738cs.CL
收藏

基于向量余弦的APSyn相似性估计测试

Testing APSyn against Vector Cosine on Similarity Estimation

The Hong Kong Polytechnic University(香港理工大学);Aix-Marseille University(艾克斯-马赛大学);University of Pisa(比萨大学)

Enrico Santus, Emmanuele Chersoni, Alessandro Lenci, Chu-Ren Huang, Philippe Blache

摘要:

在分布式语义模型(DSM)中,向量余弦被广泛用于估计词向量之间的相似度,尽管这种度量被注意到有几个缺点。最近的文献提出了其他方法,试图减轻这种偏见。在本文中,我们打算调查APSyn,一个衡量标准,计算两个目标词的最相关的上下文之间的交集的程度,加权上下文相关性。我们在几个流行的测试集上的相似性估计任务中评估了这个度量,我们的结果表明,APSyn实际上是非常有竞争力的,即使是相对于文献中报道的词嵌入的结果。最重要的是,APSyn解决了矢量余弦的一些弱点,在真正的相似性估计上也表现良好。

英文摘要:

In Distributional Semantic Models (DSMs), Vector Cosine is widely used to estimate similarity between word vectors, although this measure was noticed to suffer from several shortcomings. The recent literature has proposed other methods which attempt to mitigate such biases. In this paper, we intend to investigate APSyn, a measure that computes the extent of the intersection between the most associated contexts of two target words, weighting it by context relevance. We evaluated this metric in a similarity estimation task on several popular test sets, and our results show that APSyn is in fact highly competitive, even with respect to the results reported in the literature for word embeddings. On top of it, APSyn addresses some of the weaknesses of Vector Cosine, performing well also on genuine similarity estimation.

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。

↑