A Multiplicative Model for Learning Distributed Text-Based Attribute Representations

TL;DR

This paper introduces a multiplicative framework for learning distributed text attribute representations, enabling joint learning of word and attribute embeddings to capture context-dependent word meanings.

Contribution

It proposes a third-order multiplicative model that integrates attribute vectors with word context, allowing for dynamic, attribute-conditioned word similarity and text generation.

Findings

Effective in sentiment classification tasks

Enables cross-lingual document classification

Improves authorship attribution accuracy

Abstract

In this paper we propose a general framework for learning distributed representations of attributes: characteristics of text whose representations can be jointly learned with word embeddings. Attributes can correspond to document indicators (to learn sentence vectors), language indicators (to learn distributed language representations), meta-data and side information (such as the age, gender and industry of a blogger) or representations of authors. We describe a third-order model where word context and attribute vectors interact multiplicatively to predict the next word in a sequence. This leads to the notion of conditional word similarity: how meanings of words change when conditioned on different attributes. We perform several experimental tasks including sentiment classification, cross-lingual document classification, and blog authorship attribution. We also qualitatively evaluate conditional word neighbours and attribute-conditioned text generation.