Pseudo Labeling And Negative Feedback Learning For Large-scale Multi-label Domain Classification

Abstract

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.

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keykim2020pseudo

Related papers

• Alternative Pseudo-labeling For Semi-supervised Automatic Speech Recognition (2023)10.48
• Joint Speech Transcription And Translation: Pseudo-labeling With Out-of-distribution Data (2022)0.00
• Multi-objective Progressive Clustering For Semi-supervised Domain Adaptation In Speaker Verification (2023)5.24
• Boosting Cross-domain Speech Recognition With Self-supervision (2022)0.00
• Joint Learning Of Domain Classification And Out-of-domain Detection With Dynamic Class Weighting For Satisficing False Acceptance Rates (2018)10.35
• Locale-agnostic Universal Domain Classification Model In Spoken Language Understanding (2019)5.24
• Toward Domain-invariant Speech Recognition Via Large Scale Training (2018)13.39
• Boosting Active Learning For Speech Recognition With Noisy Pseudo-labeled Samples (2020)0.00