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

• URL: http://arxiv.org/abs/2003.03504v1
• Date: Sat, 7 Mar 2020 03:29:01 GMT
• Title: A Post-processing Method for Detecting Unknown Intent of Dialogue System via Pre-trained Deep Neural Network Classifier
• Authors: Ting-En Lin, Hua Xu
• Abstract summary: We propose SofterMax and deep novelty detection (SMDN) for detecting unknown intent in dialogue systems. Our method can be flexibly applied on top of any classifiers trained in deep neural networks without changing the model architecture. Our method classifies examples that differ from known intents as unknown and does not require any examples or prior knowledge of it.
• Score: 23.25650237235107
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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

Related papers

• Deception Detection from Linguistic and Physiological Data Streams Using Bimodal Convolutional Neural Networks [19.639533220155965]
  This paper explores the application of convolutional neural networks for the purpose of multimodal deception detection. We use a dataset built by interviewing 104 subjects about two topics, with one truthful and one falsified response from each subject about each topic.
  arXiv  Detail & Related papers  (2023-11-18T02:44:33Z)
• Large-Scale Sequential Learning for Recommender and Engineering Systems [91.3755431537592]
  In this thesis, we focus on the design of an automatic algorithms that provide personalized ranking by adapting to the current conditions. For the former, we propose novel algorithm called SAROS that take into account both kinds of feedback for learning over the sequence of interactions. The proposed idea of taking into account the neighbour lines shows statistically significant results in comparison with the initial approach for faults detection in power grid.
  arXiv  Detail & Related papers  (2022-05-13T21:09:41Z)
• Neural Maximum A Posteriori Estimation on Unpaired Data for Motion Deblurring [87.97330195531029]
  We propose a Neural Maximum A Posteriori (NeurMAP) estimation framework for training neural networks to recover blind motion information and sharp content from unpaired data. The proposed NeurMAP is an approach to existing deblurring neural networks, and is the first framework that enables training image deblurring networks on unpaired datasets.
  arXiv  Detail & Related papers  (2022-04-26T08:09:47Z)
• A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networks [2.578242050187029]
  We introduce the unknown detection task, an integration of previous individual tasks. We find that Deep Ensemble consistently outperforms the other approaches in detecting unknowns.
  arXiv  Detail & Related papers  (2021-12-01T08:07:01Z)
• Collective Decision of One-vs-Rest Networks for Open Set Recognition [0.0]
  We propose a simple open set recognition (OSR) method based on the intuition that OSR performance can be maximized by setting strict and sophisticated decision boundaries. The proposed method performed significantly better than the state-of-the-art methods by effectively reducing overgeneralization.
  arXiv  Detail & Related papers  (2021-03-18T13:06:46Z)
• Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference [150.07326223077405]
  Few-shot learning is attracting much attention to mitigate data scarcity. We present a discriminative nearest neighbor classification with deep self-attention. We propose to boost the discriminative ability by transferring a natural language inference (NLI) model.
  arXiv  Detail & Related papers  (2020-10-25T00:39:32Z)
• ESPN: Extremely Sparse Pruned Networks [50.436905934791035]
  We show that a simple iterative mask discovery method can achieve state-of-the-art compression of very deep networks. Our algorithm represents a hybrid approach between single shot network pruning methods and Lottery-Ticket type approaches.
  arXiv  Detail & Related papers  (2020-06-28T23:09:27Z)
• Few-Shot Open-Set Recognition using Meta-Learning [72.15940446408824]
  The problem of open-set recognition is considered. A new oPen sEt mEta LEaRning (PEELER) algorithm is introduced.
  arXiv  Detail & Related papers  (2020-05-27T23:49:26Z)
• AutoSpeech: Neural Architecture Search for Speaker Recognition [108.69505815793028]
  We propose the first neural architecture search approach approach for the speaker recognition tasks, named as AutoSpeech. Our algorithm first identifies the optimal operation combination in a neural cell and then derives a CNN model by stacking the neural cell for multiple times. Results demonstrate that the derived CNN architectures significantly outperform current speaker recognition systems based on VGG-M, ResNet-18, and ResNet-34 back-bones, while enjoying lower model complexity.
  arXiv  Detail & Related papers  (2020-05-07T02:53:47Z)
• Conditional Gaussian Distribution Learning for Open Set Recognition [10.90687687505665]
  We propose Conditional Gaussian Distribution Learning (CGDL) for open set recognition. In addition to detecting unknown samples, this method can also classify known samples by forcing different latent features to approximate different Gaussian models. Experiments on several standard image reveal that the proposed method significantly outperforms the baseline method and achieves new state-of-the-art results.
  arXiv  Detail & Related papers  (2020-03-19T14:32:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.