# A Post-processing Method for Detecting Unknown Intent of Dialogue System via Pre-trained Deep Neural Network Classifier

arXiv: https://arxiv.org/abs/2003.03504 · HTML: https://mlsanity.com/paper/2003.03504/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Mar 2020.

## Built on by (most cited first, 11 of 11)

- [UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition](https://mlsanity.com/paper/2211.11256/) (2022)
- [Open-world Machine Learning: Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2105.13448/) (2021)
- [Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systems](https://mlsanity.com/paper/2205.15060/) (2022)
- [Learning Discriminative Representations and Decision Boundaries for Open Intent Detection](https://mlsanity.com/paper/2203.05823/) (2022)
- [LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition](https://mlsanity.com/paper/2309.12780/) (2023)
- [Out-of-Scope Domain and Intent Classification through Hierarchical Joint Modeling](https://mlsanity.com/paper/2104.14781/) (2021)
- [Open World Classification with Adaptive Negative Samples](https://mlsanity.com/paper/2303.05581/) (2023)
- [Intent-calibrated Self-training for Answer Selection in Open-domain Dialogues](https://mlsanity.com/paper/2307.06703/) (2023)
- [Continuous representations of intents for dialogue systems](https://mlsanity.com/paper/2105.03716/) (2021)
- [OpenCML: End-to-End Framework of Open-world Machine Learning to Learn Unknown Classes Incrementally](https://mlsanity.com/paper/2511.19491/) (2025)
- [Open-Set Domain Adaptation Under Background Distribution Shift: Challenges and A Provably Efficient Solution](https://mlsanity.com/paper/2512.01152/) (2025)

## Abstract (arXiv)

With the maturity and popularity of dialogue systems, detecting user's unknown intent in dialogue systems has become an important task. It is also one of the most challenging tasks since we can hardly get examples, prior knowledge or the exact numbers of unknown intents. In this paper, we propose SofterMax and deep novelty detection (SMDN), a simple yet effective post-processing method for detecting unknown intent in dialogue systems based on pre-trained deep neural network classifiers. Our method can be flexibly applied on top of any classifiers trained in deep neural networks without changing the model architecture. We calibrate the confidence of the softmax outputs to compute the calibrated confidence score (i.e., SofterMax) and use it to calculate the decision boundary for unknown intent detection. Furthermore, we feed the feature representations learned by the deep neural networks into traditional novelty detection algorithm to detect unknown intents from different perspectives. Finally, we combine the methods above to perform the joint prediction. Our method classifies examples that differ from known intents as unknown and does not require any examples or prior knowledge of it. We have conducted extensive experiments on three benchmark dialogue datasets. The results show that our method can yield significant improvements compared with the state-of-the-art baselines