Post-Specialisation: Retrofitting Vectors of Words Unseen in Lexical Resources

TL;DR

This paper introduces a novel post-specialisation method that propagates external lexical knowledge to unseen words in word vector spaces using a deep neural network, improving their representations for various NLP tasks across multiple languages.

Contribution

It extends word vector specialisation to unseen words by learning a non-linear transformation, enhancing the entire vocabulary's quality in distributional spaces.

Findings

Significant improvements in word similarity tasks

Enhanced performance in dialogue state tracking

Better results in lexical text simplification

Abstract

Word vector specialisation (also known as retrofitting) is a portable, light-weight approach to fine-tuning arbitrary distributional word vector spaces by injecting external knowledge from rich lexical resources such as WordNet. By design, these post-processing methods only update the vectors of words occurring in external lexicons, leaving the representations of all unseen words intact. In this paper, we show that constraint-driven vector space specialisation can be extended to unseen words. We propose a novel post-specialisation method that: a) preserves the useful linguistic knowledge for seen words; while b) propagating this external signal to unseen words in order to improve their vector representations as well. Our post-specialisation approach explicits a non-linear specialisation function in the form of a deep neural network by learning to predict specialised vectors from their original distributional counterparts. The learned function is then used to specialise vectors of unseen words. This approach, applicable to any post-processing model, yields considerable gains over the initial specialisation models both in intrinsic word similarity tasks, and in two downstream tasks: dialogue state tracking and lexical text simplification. The positive effects persist across three languages, demonstrating the importance of specialising the full vocabulary of distributional word vector spaces.