Collaborative Training of Tensors for Compositional Distributional Semantics

TL;DR

This paper introduces parameter-sharing training methods for compositional distributional semantic models, enabling zero-shot learning and high-quality tensor construction from limited data.

Contribution

It proposes novel training techniques that share parameters among similar words, allowing effective learning with minimal data and zero-shot capabilities.

Findings

Enables zero-shot learning for unseen words.

Constructs high-quality tensors from few examples.

Improves training efficiency for semantic models.

Abstract

Type-based compositional distributional semantic models present an interesting line of research into functional representations of linguistic meaning. One of the drawbacks of such models, however, is the lack of training data required to train each word-type combination. In this paper we address this by introducing training methods that share parameters between similar words. We show that these methods enable zero-shot learning for words that have no training data at all, as well as enabling construction of high-quality tensors from very few training examples per word.