Collaborative Training of Tensors for Compositional Distributional Semantics
This addresses a data scarcity problem in computational linguistics, enabling more efficient semantic modeling.
The paper tackles the lack of training data for type-based compositional distributional semantic models by introducing parameter-sharing methods, resulting in zero-shot learning for words without data and high-quality tensors from few examples.
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.