Generative Topic Embedding: a Continuous Representation of Documents (Extended Version with Proofs)

TL;DR

This paper introduces a generative topic embedding model that combines local word context and global document-level topic patterns into a unified continuous representation, improving classification and topic coherence.

Contribution

It proposes a novel model that jointly learns topic embeddings and document representations, integrating local and global word patterns for better document analysis.

Findings

Outperforms eight existing methods in classification tasks

Requires fewer features for comparable or better performance

Can generate coherent topics from a single document

Abstract

Word embedding maps words into a low-dimensional continuous embedding space by exploiting the local word collocation patterns in a small context window. On the other hand, topic modeling maps documents onto a low-dimensional topic space, by utilizing the global word collocation patterns in the same document. These two types of patterns are complementary. In this paper, we propose a generative topic embedding model to combine the two types of patterns. In our model, topics are represented by embedding vectors, and are shared across documents. The probability of each word is influenced by both its local context and its topic. A variational inference method yields the topic embeddings as well as the topic mixing proportions for each document. Jointly they represent the document in a low-dimensional continuous space. In two document classification tasks, our method performs better than eight existing methods, with fewer features. In addition, we illustrate with an example that our method can generate coherent topics even based on only one document.