Multi-Step Regression Learning for Compositional Distributional Semantics

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.

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

Cited by in corpus (8)

• Efficient Vector Representation for Documents through Corruption
• Distributed Representations for Biological Sequence Analysis
• Distributed Representations for Compositional Semantics
• Semantic Composition via Probabilistic Model Theory
• Linguistic Matrix Theory
• Paraphrase-Supervised Models of Compositionality
• A Factorized Model for Transitive Verbs in Compositional Distributional Semantics
• Resolving Lexical Ambiguity in Tensor Regression Models of Meaning