Multi-Step Regression Learning for Compositional Distributional Semantics

Multi-Step Regression Learning for Compositional Distributional Semantics
复制标题

DOI:
--
复制
发表时间:
2013-01
期刊:
--
影响因子:
--
通讯作者:
Edward Grefenstette;Georgiana Dinu;Yao-zhong Zhang;M. Sadrzadeh;Marco Baroni
Edward Grefenstette;Georgiana Dinu;Yao-zhong Zhang;M. Sadrzadeh;Marco Baroni
中科院分区:
其他
文献类型:
--
作者:
Edward Grefenstette;Georgiana Dinu;Yao-zhong Zhang;M. Sadrzadeh;Marco Baroni

文献摘要

被引文献

相似文献

我们提出了一个与Coecke等人(2010)的框架相关的组合分布语义模型,并通过将函数表示为张量,将参数表示为向量来模拟形式语义。我们引入了一种新的张量学习方法,推广了Baroni和Zamparelli(2010)的方法。我们在两个基准数据集上对其进行了评估,并发现它优于现有的主要方法。在我们的分析中,我们认为这种学习方法的本质也使得它适合于解决组合分布模型可能面临的更微妙的问题。
We present a model for compositional distributional semantics related to the framework of Coecke et al. (2010), and emulating formal semantics by representing functions as tensors and arguments as vectors. We introduce a new learning method for tensors, generalising the approach of Baroni and Zamparelli (2010). We evaluate it on two benchmark data sets, and find it to outperform existing leading methods. We argue in our analysis that the nature of this learning method also renders it suitable for solving more subtle problems compositional distributional models might face.