DOC: Deep Open Classification of Text Documents

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.

accepted at EMNLP 2017

References in corpus (2)

• Convolutional Neural Networks for Sentence Classification
• Lifelong Learning CRF for Supervised Aspect Extraction

Cited by in corpus (9)

• Deep Learning for Anomaly Detection: A Survey
• Recent Advances in Open Set Recognition: A Survey
• Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness
• Automatic Discovery of Novel Intents & Domains from Text Utterances
• Open Set Recognition with Conditional Probabilistic Generative Models
• Hybrid Models for Open Set Recognition
• Class Anchor Clustering: a Loss for Distance-based Open Set Recognition
• Adaptive Image Stream Classification via Convolutional Neural Network with Intrinsic Similarity Metrics
• Text Classification with Novelty Detection