An end-to-end Neural Network Framework for Text Clustering

TL;DR

This paper introduces an end-to-end neural network framework for text clustering that jointly learns text representations and clustering, outperforming traditional multi-step methods on benchmark datasets.

Contribution

The proposed neural framework unifies text representation learning and clustering into a single end-to-end model, improving clustering performance in NLP tasks.

Findings

Outperforms previous clustering methods significantly

Effective on multiple benchmark datasets

Works well with large corpora

Abstract

The unsupervised text clustering is one of the major tasks in natural language processing (NLP) and remains a difficult and complex problem. Conventional \mbox{methods} generally treat this task using separated steps, including text representation learning and clustering the representations. As an improvement, neural methods have also been introduced for continuous representation learning to address the sparsity problem. However, the multi-step process still deviates from the unified optimization target. Especially the second step of cluster is generally performed with conventional methods such as k-Means. We propose a pure neural framework for text clustering in an end-to-end manner. It jointly learns the text representation and the clustering model. Our model works well when the context can be obtained, which is nearly always the case in the field of NLP. We have our method \mbox{evaluated} on two widely used benchmarks: IMDB movie reviews for sentiment classification and $20$-Newsgroup for topic categorization. Despite its simplicity, experiments show the model outperforms previous clustering methods by a large margin. Furthermore, the model is also verified on English wiki dataset as a large corpus.