English

Multi-Step Regression Learning for Compositional Distributional Semantics

Computation and Language 2013-01-31 v2 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1301.6939,
  title  = {Multi-Step Regression Learning for Compositional Distributional Semantics},
  author = {Edward Grefenstette and Georgiana Dinu and Yao-Zhong Zhang and Mehrnoosh Sadrzadeh and Marco Baroni},
  journal= {arXiv preprint arXiv:1301.6939},
  year   = {2013}
}

Comments

10 pages + 1 page references, to be presented at the 10th International Conference on Computational Semantics (IWCS 2013)

R2 v1 2026-06-21T23:17:10.882Z