DOC: Deep Open Classification of Text Documents

TL;DR

This paper introduces a deep learning approach for open-world text classification that effectively identifies novel documents not seen during training, outperforming existing methods significantly.

Contribution

It presents a novel deep learning method for open classification of text documents, addressing the challenge of detecting unseen classes during testing.

Findings

Outperforms state-of-the-art techniques dramatically

Effective in identifying novel, unseen documents

Advances open-world text classification capabilities

Abstract

Traditional supervised learning makes the closed-world assumption that the classes appeared in the test data must have appeared in training. This also applies to text learning or text classification. As learning is used increasingly in dynamic open environments where some new/test documents may not belong to any of the training classes, identifying these novel documents during classification presents an important problem. This problem is called open-world classification or open classification. This paper proposes a novel deep learning based approach. It outperforms existing state-of-the-art techniques dramatically.