# Neural Models for Documents with Metadata

## TL;DR

This paper introduces a neural framework based on topic models that effectively incorporates metadata into document modeling, enabling flexible, rapid exploration of models with strong performance on real-world data.

## Contribution

It presents a general neural approach leveraging variational inference to incorporate metadata into topic models, simplifying customization and exploration.

## Key findings

- Achieves strong perplexity, coherence, and sparsity tradeoffs.
- Demonstrates effectiveness on US immigration articles.
- Provides a flexible framework for metadata integration.

## Abstract

Most real-world document collections involve various types of metadata, such as author, source, and date, and yet the most commonly-used approaches to modeling text corpora ignore this information. While specialized models have been developed for particular applications, few are widely used in practice, as customization typically requires derivation of a custom inference algorithm. In this paper, we build on recent advances in variational inference methods and propose a general neural framework, based on topic models, to enable flexible incorporation of metadata and allow for rapid exploration of alternative models. Our approach achieves strong performance, with a manageable tradeoff between perplexity, coherence, and sparsity. Finally, we demonstrate the potential of our framework through an exploration of a corpus of articles about US immigration.