A Multiplicative Model for Learning Distributed Text-Based Attribute Representations
This work addresses the need for better integration of metadata and side information in text representation learning, offering a general framework applicable to various NLP tasks, though it is incremental in nature.
The authors tackled the problem of learning distributed representations for text attributes by proposing a third-order multiplicative model that jointly learns word and attribute embeddings, achieving improved performance on sentiment classification, cross-lingual document classification, and blog authorship attribution tasks.
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.