Low-Rank Tensors for Verbs in Compositional Distributional Semantics
Low-Rank Tensors for Verbs in Compositional Distributional Semantics
复制标题
DOI：
10.3115/v1/p15-2120
复制
发表时间：
2015-07
期刊：
影响因子：
--
通讯作者：
Daniel Fried;T. Polajnar;S. Clark
中科院分区：
文献类型：
--
作者：
Daniel Fried;T. Polajnar;S. Clark
几种组合分布语义方法使用张量来模拟向量之间的多路交互。不幸的是，张量的大小可能使它们在大规模实现中的使用变得不切实际。在本文中，我们研究是否可以匹配的性能与低秩近似，使用一小部分的原始参数的完整张量。我们研究了低秩张量对动词为三阶张量的及物动词结构的影响。结果表明，虽然低秩张量需要每个动词少两个数量级的参数，但它们在句子相似性和动词disam方面的性能与无约束秩张量相当，有时甚至超过无约束秩张量。
Several compositional distributional semantic methods use tensors to model multi-way interactions between vectors. Unfortunately, the size of the tensors can make their use impractical in large-scale implementations. In this paper, we investigate whether we can match the performance of full tensors with low-rank approximations that use a fraction of the original number of parameters. We investigate the effect of low-rank tensors on the transitive verb construction where the verb is a third-order tensor. The results show that, while the low-rank tensors require about two orders of magnitude fewer parameters per verb, they achieve performance comparable to, and occasionally surpassing, the unconstrained-rank tensors on sentence similarity and verb disam-