Deep Open Intent Classification with Adaptive Decision Boundary

• URL: http://arxiv.org/abs/2012.10209v5
• Date: Thu, 1 Apr 2021 13:27:49 GMT
• Title: Deep Open Intent Classification with Adaptive Decision Boundary
• Authors: Hanlei Zhang, Hua Xu, Ting-En Lin
• Abstract summary: We propose a post-processing method to learn the adaptive decision boundary (ADB) for open intent classification. Specifically, we propose a new loss function to balance both the empirical risk and the open space risk. Our approach is surprisingly insensitive with less labeled data and fewer known intents.
• Score: 21.478553057876972
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Open intent classification is a challenging task in dialogue systems. On the one hand, it should ensure the quality of known intent identification. On the other hand, it needs to detect the open (unknown) intent without prior knowledge. Current models are limited in finding the appropriate decision boundary to balance the performances of both known intents and the open intent. In this paper, we propose a post-processing method to learn the adaptive decision boundary (ADB) for open intent classification. We first utilize the labeled known intent samples to pre-train the model. Then, we automatically learn the adaptive spherical decision boundary for each known class with the aid of well-trained features. Specifically, we propose a new loss function to balance both the empirical risk and the open space risk. Our method does not need open intent samples and is free from modifying the model architecture. Moreover, our approach is surprisingly insensitive with less labeled data and fewer known intents. Extensive experiments on three benchmark datasets show that our method yields significant improvements compared with the state-of-the-art methods. The codes are released at https://github.com/thuiar/Adaptive-Decision-Boundary.

Related papers

• Learnability Gaps of Strategic Classification [68.726857356532]
  We focus on addressing a fundamental question: the learnability gaps between strategic classification and standard learning. We provide nearly tight sample complexity and regret bounds, offering significant improvements over prior results. Notably, our algorithm in this setting is of independent interest and can be applied to other problems such as multi-label learning.
  arXiv  Detail & Related papers  (2024-02-29T16:09:19Z)
• Effective Open Intent Classification with K-center Contrastive Learning and Adjustable Decision Boundary [28.71330804762103]
  We introduce novel K-center contrastive learning and adjustable decision boundary learning (CLAB) to improve the effectiveness of open intent classification. Specifically, we devise a K-center contrastive learning algorithm to learn discriminative and balanced intent features. We then learn a decision boundary for each known intent class, which consists of a decision center and the radius of the decision boundary.
  arXiv  Detail & Related papers  (2023-04-20T11:35:06Z)
• Open World Classification with Adaptive Negative Samples [89.2422451410507]
  Open world classification is a task in natural language processing with key practical relevance and impact. We propose an approach based on underlineadaptive underlinesamples (ANS) designed to generate effective synthetic open category samples in the training stage. ANS achieves significant improvements over state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-03-09T21:12:46Z)
• Discovering New Intents Using Latent Variables [51.50374666602328]
  We propose a probabilistic framework for discovering intents where intent assignments are treated as latent variables. In E-step, we conduct discovering intents and explore the intrinsic structure of unlabeled data by the posterior of intent assignments. In M-step, we alleviate the forgetting of prior knowledge transferred from known intents by optimizing the discrimination of labeled data.
  arXiv  Detail & Related papers  (2022-10-21T08:29:45Z)
• Learning to Classify Open Intent via Soft Labeling and Manifold Mixup [10.863749481341497]
  Open intent classification is a practical yet challenging task in dialogue systems. We consider another way without using outlier detection algorithms. We propose a deep model based on Soft Labeling and Manifold Mixup.
  arXiv  Detail & Related papers  (2022-04-16T14:10:07Z)
• Learning Discriminative Representations and Decision Boundaries for Open Intent Detection [16.10123071366136]
  Open intent detection is a significant problem in natural language understanding. We propose DA-ADB, which learns distance-aware intent representations and adaptive decision boundaries for open intent detection. Our framework achieves substantial improvements on three benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-11T10:02:09Z)
• Discovering New Intents with Deep Aligned Clustering [19.11073686645496]
  We propose an effective method, Deep Aligned Clustering, to discover new intents with the aid of limited known intent data. With an unknown number of new intents, we predict the number of intent categories by eliminating low-confidence intent-wise clusters. Experiments on two benchmark datasets show that our method is more robust and achieves substantial improvements over the state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-12-16T14:32:06Z)
• 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)
• Open Set Recognition with Conditional Probabilistic Generative Models [51.40872765917125]
  We propose Conditional Probabilistic Generative Models (CPGM) for open set recognition. CPGM can detect unknown samples but also classify known classes by forcing different latent features to approximate conditional Gaussian distributions. Experiment results on multiple benchmark datasets reveal that the proposed method significantly outperforms the baselines.
  arXiv  Detail & Related papers  (2020-08-12T06:23:49Z)
• 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)

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.