# Learning with Noisy Labels for Sentence-level Sentiment Classification

arXiv: https://arxiv.org/abs/1909.00124 · HTML: https://mlsanity.com/paper/1909.00124/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Aug 2019.

## Built on by (most cited first, 11 of 11)

- [Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective](https://mlsanity.com/paper/2112.06409/) (2021)
- [Learning from Noisy Labels for Entity-Centric Information Extraction](https://mlsanity.com/paper/2104.08656/) (2021)
- [Analysing the Noise Model Error for Realistic Noisy Label Data](https://mlsanity.com/paper/2101.09763/) (2021)
- [Clean or Annotate: How to Spend a Limited Data Collection Budget](https://mlsanity.com/paper/2110.08355/) (2021)
- [CrowdChecked: Detecting Previously Fact-Checked Claims in Social Media](https://mlsanity.com/paper/2210.04447/) (2022)
- [End-to-End Annotator Bias Approximation on Crowdsourced Single-Label Sentiment Analysis](https://mlsanity.com/paper/2111.02326/) (2021)
- [An Introduction to Robust Graph Convolutional Networks](https://mlsanity.com/paper/2103.14807/) (2021)
- [Sources of Noise in Dialogue and How to Deal with Them](https://mlsanity.com/paper/2212.02745/) (2022)
- [Integrated Weak Learning](https://mlsanity.com/paper/2206.09496/) (2022)
- [Low Resource Pipeline for Spoken Language Understanding via Weak Supervision](https://mlsanity.com/paper/2206.10559/) (2022)
- [On-the-fly Denoising for Data Augmentation in Natural Language Understanding](https://mlsanity.com/paper/2212.10558/) (2022)

## Abstract (arXiv)

Deep neural networks (DNNs) can fit (or even over-fit) the training data very well. If a DNN model is trained using data with noisy labels and tested on data with clean labels, the model may perform poorly. This paper studies the problem of learning with noisy labels for sentence-level sentiment classification. We propose a novel DNN model called NetAb (as shorthand for convolutional neural Networks with Ab-networks) to handle noisy labels during training. NetAb consists of two convolutional neural networks, one with a noise transition layer for dealing with the input noisy labels and the other for predicting 'clean' labels. We train the two networks using their respective loss functions in a mutual reinforcement manner. Experimental results demonstrate the effectiveness of the proposed model.