Learning with Noisy Labels for Sentence-level Sentiment Classification

Wang, Hao; Liu, Bing; Li, Chaozhuo; Yang, Yan; Li, Tianrui

doi:10.18653/v1/d19-1655

Cited by 47 publications

(28 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To avoid this, it can be combined with label noise handling techniques. This pipeline has been shown to be effective for several NLP tasks (Lange et al, 2019;Paul et al, 2019;Wang et al, 2019;Chen et al, 2019;Mayhew et al, 2019), however, mostly for RNN based approaches. As we have seen in Section 4 that these have a lower baseline performance, we are interested in whether distant supervision is still useful for the better performing transformer models.…”

Section: Distant Supervisionmentioning

confidence: 99%

See 1 more Smart Citation

Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages

Hedderich

Adelani

Zhu

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Multilingual transformer models like mBERT and XLM-RoBERTa have obtained great improvements for many NLP tasks on a variety of languages. However, recent works also showed that results from high-resource languages could not be easily transferred to realistic, low-resource scenarios. In this work, we study trends in performance for different amounts of available resources for the three African languages Hausa, isiXhosa and Yorùbá on both NER and topic classification. We show that in combination with transfer learning or distant supervision, these models can achieve with as little as 10 or 100 labeled sentences the same performance as baselines with much more supervised training data. However, we also find settings where this does not hold. Our discussions and additional experiments on assumptions such as time and hardware restrictions highlight challenges and opportunities in low-resource learning.

show abstract

Section: Distant Supervisionmentioning

confidence: 99%

“…We use a confusion matrix which is a common approach for handling noisy labels (see, e.g. (Fang and Cohn, 2016;Luo et al, 2017;Lange et al, 2019;Wang et al, 2019)). The confusion matrix models the relationship between the true, clean label of an instance and its corresponding noisy label.…”

Section: E4 Transfer Learningmentioning

confidence: 99%

Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages

Hedderich

Adelani

Zhu

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

show abstract

“…For aspect classification, Karamanolakis et al (2019) create a simple bag-of-words classifier on a list of seed words and train a deep neural network on its weak supervision. Wang et al (2019) use context by transferring a documentlevel sentiment label to all its sentence-level in-stances. Mekala et al (2020) leverage meta-data for text classification and Huber and Carenini (2020) build a discourse-structure dataset using guidance from sentiment annotations.…”

Section: Distant and Weak Supervisionmentioning

confidence: 99%

“…The noise in the labels can also be modeled. A common model is a confusion matrix estimating the relationship between clean and noisy labels (Fang and Cohn, 2016;Luo et al, 2017;Hedderich and Klakow, 2018;Paul et al, 2019;Lange et al, 2019a,c;Wang et al, 2019;Hedderich et al, 2021b). The classifier is no longer trained directly on the noisily-labeled data.…”

Section: Learning With Noisy Labelsmentioning

confidence: 99%

A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios

Hedderich¹,

Lange²,

Adel³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

104

View full text Add to dashboard Cite

Deep neural networks and huge language models are becoming omnipresent in natural language applications. As they are known for requiring large amounts of training data, there is a growing body of work to improve the performance in low-resource settings. Motivated by the recent fundamental changes towards neural models and the popular pre-train and fine-tune paradigm, we survey promising approaches for low-resource natural language processing. After a discussion about the different dimensions of data availability, we give a structured overview of methods that enable learning when training data is sparse. This includes mechanisms to create additional labeled data like data augmentation and distant supervision as well as transfer learning settings that reduce the need for target supervision. A goal of our survey is to explain how these methods differ in their requirements as understanding them is essential for choosing a technique suited for a specific low-resource setting. Further key aspects of this work are to highlight open issues and to outline promising directions for future research.

show abstract

“…The most prominent idea in this line is to estimate the noise transition matrix among labels Goldberger and Ben-Reuven, 2016;Wang et al, 2019;Northcutt et al, 2019) and then use the transition matrices to re-label the instances or adapt the loss functions. Specifically, Wang et al (2019) and Northcutt et al (2019) generate label noise by flipping clean labels based on such noise transition matrices. They are thus not applicable to our weak supervision setting where no clean labels are given.…”

Section: Related Workmentioning

confidence: 99%

Denoising Multi-Source Weak Supervision for Neural Text Classification

Ren¹,

Li²,

Su³

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

View full text Add to dashboard Cite

We study the problem of learning neural text classifiers without using any labeled data, but only easy-to-provide rules as multiple weak supervision sources. This problem is challenging because rule-induced weak labels are often noisy and incomplete. To address these two challenges, we design a label denoiser, which estimates the source reliability using a conditional soft attention mechanism and then reduces label noise by aggregating rule-annotated weak labels. The denoised pseudo labels then supervise a neural classifier to predicts soft labels for unmatched samples, which address the rule coverage issue. We evaluate our model on five benchmarks for sentiment, topic, and relation classifications.The results show that our model outperforms state-of-the-art weakly-supervised and semi-supervised methods consistently, and achieves comparable performance with fully-supervised methods even without any labeled data. Our code can be found at https://github.com/weakrules/ Denoise-multi-weak-sources.

show abstract

Learning with Noisy Labels for Sentence-level Sentiment Classification

Cited by 47 publications

References 31 publications

Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages

Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages

A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios

Denoising Multi-Source Weak Supervision for Neural Text Classification

Contact Info

Product

Resources

About