Estimating Linear Models for Compositional Distributional Semantics
Estimating Linear Models for Compositional Distributional Semantics
复制标题
DOI：
--
复制
发表时间：
2010-08
期刊：
影响因子：
--
通讯作者：
Fabio Massimo Zanzotto;Ioannis Korkontzelos;Francesca Fallucchi;S. Manandhar
中科院分区：
文献类型：
--
作者：
Fabio Massimo Zanzotto;Ioannis Korkontzelos;Francesca Fallucchi;S. Manandhar
在分布语义学研究中，从成分上确定词序列的分布意义越来越受到关注。然而，成分分布模型依赖于一组尚未探索的参数。在本文中，我们提出了一种新的方法来估计一类组成分布模型的参数：可加性模型。我们的方法利用了两个主要思想。首先，提出了一种提取组合分布语义实例的新思想。第二，基于回归模型的多因变量估计方法。实验表明，我们的方法优于现有的方法来确定一个好的模型组成的分布语义。
In distributional semantics studies, there is a growing attention in compositionally determining the distributional meaning of word sequences. Yet, compositional distributional models depend on a large set of parameters that have not been explored. In this paper we propose a novel approach to estimate parameters for a class of compositional distributional models: the additive models. Our approach leverages on two main ideas. Firstly, a novel idea for extracting compositional distributional semantics examples. Secondly, an estimation method based on regression models for multiple dependent variables. Experiments demonstrate that our approach outperforms existing methods for determining a good model for compositional distributional semantics.