Pseudo Labeling and Negative Feedback Learning for Large-scale Multi-label Domain Classification
In large-scale domain classification, an utterance can be handled by multiple domains with overlapped capabilities. However, only a limited number of ground-truth domains are provided for each training utterance in practice while knowing as many as correct target labels is helpful for improving the model performance. In this paper, given one ground-truth domain for each training utterance, we regard domains consistently predicted with the highest confidences as additional pseudo labels for the training. In order to reduce prediction errors due to incorrect pseudo labels, we leverage utterances with negative system responses to decrease the confidences of the incorrectly predicted domains. Evaluating on user utterances from an intelligent conversational system, we show that the proposed approach significantly improves the performance of domain classification with hypothesis reranking.
Code (0)
등록된 구현이 없습니다.
Tasks
domain classificationGeneral ClassificationRerankingSimilar Papers 제목 키워드 기반
More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning
Multi-label learning is a challenging computer vision task that requires assigning multiple categories to each image. However, fully annotating large-scale datasets is often impractical due to high costs and effort, moti…
Multi-Label ClassificationMulti-Label LearningSemi-Supervised Domain Generalization with Evolving Intermediate Domain
Domain Generalization (DG) aims to generalize a model trained on multiple source domains to an unseen target domain. The source domains always require precise annotations, which can be cumbersome or even infeasible to ob…
Domain GeneralizationSemi-Supervised Domain GeneralizationIn Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning
The recent research in semi-supervised learning (SSL) is mostly dominated by consistency regularization based methods which achieve strong performance. However, they heavily rely on domain-specific data augmentations, wh…
Multi-Label ClassificationMUlTI-LABEL-ClASSIFICATIONPseudo LabelSemi-Supervised Image Classification+2Generative Pseudo-Labeling for Pre-Ranking with LLMs
Pre-ranking is a critical stage in industrial recommendation systems, tasked with efficiently scoring thousands of recalled items for downstream ranking. A key challenge is the train-serving discrepancy: pre-ranking mode…
Recommendation SystemsTrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detection
Semi-supervised 3D object detection is a common strategy employed to circumvent the challenge of manually labeling large-scale autonomous driving perception datasets. Pseudo-labeling approaches to semi-supervised learnin…
3D Object DetectionAutonomous DrivingMotion ForecastingObject+3