# Pseudo Labeling and Negative Feedback Learning for Large-scale Multi-label Domain Classification

arXiv: https://arxiv.org/abs/2003.03728 · HTML: https://mlsanity.com/paper/2003.03728/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Mar 2020.

## Built on by (most cited first, 6 of 6)

- [Deciding Whether to Ask Clarifying Questions in Large-Scale Spoken Language Understanding](https://mlsanity.com/paper/2109.12451/) (2021)
- [Federated Learning with Noisy User Feedback](https://mlsanity.com/paper/2205.03092/) (2022)
- [Couple Learning for semi-supervised sound event detection](https://mlsanity.com/paper/2110.05809/) (2021)
- [Cluster-Guided Label Generation in Extreme Multi-Label Classification](https://mlsanity.com/paper/2302.09150/) (2023)
- [Category-wise Fine-Tuning: Resisting Incorrect Pseudo-Labels in Multi-Label Image Classification with Partial Labels](https://mlsanity.com/paper/2401.16991/) (2024)
- [Two-stage Voice Application Recommender System for Unhandled Utterances in Intelligent Personal Assistant](https://mlsanity.com/paper/2110.09877/) (2021)

## Abstract (arXiv)

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.