# Categorical Metadata Representation for Customized Text Classification

## TL;DR

This paper introduces a novel basis vector approach for representing categorical metadata in neural text classification models, significantly improving performance and parameter efficiency over existing methods.

## Contribution

The paper proposes a basis vector method for encoding categorical metadata, outperforming traditional representation techniques and reducing model complexity.

## Key findings

- The basis vector method improves classification accuracy across multiple datasets.
- It reduces the number of parameters needed for categorical feature representation.
- The approach enhances model customization using categorical metadata.

## Abstract

The performance of text classification has improved tremendously using intelligently engineered neural-based models, especially those injecting categorical metadata as additional information, e.g., using user/product information for sentiment classification. These information have been used to modify parts of the model (e.g., word embeddings, attention mechanisms) such that results can be customized according to the metadata. We observe that current representation methods for categorical metadata, which are devised for human consumption, are not as effective as claimed in popular classification methods, outperformed even by simple concatenation of categorical features in the final layer of the sentence encoder. We conjecture that categorical features are harder to represent for machine use, as available context only indirectly describes the category, and even such context is often scarce (for tail category). To this end, we propose to use basis vectors to effectively incorporate categorical metadata on various parts of a neural-based model. This additionally decreases the number of parameters dramatically, especially when the number of categorical features is large. Extensive experiments on various datasets with different properties are performed and show that through our method, we can represent categorical metadata more effectively to customize parts of the model, including unexplored ones, and increase the performance of the model greatly.