An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction
The incorporation of pseudo data in the training of grammatical error correction models has been one of the main factors in improving the performance of such models. However, consensus is lacking on experimental configurations, namely, choosing how the pseudo data should be generated or used. In this study, these choices are investigated through extensive experiments, and state-of-the-art performance is achieved on the CoNLL-2014 test set ($F_{0.5}=65.0$) and the official test set of the BEA-2019 shared task ($F_{0.5}=70.2$) without making any modifications to the model architecture.
Code (1)
Tasks
Grammatical Error CorrectionSimilar Papers 제목 키워드 기반
Pseudo Labelling for Enhanced Masked Autoencoders
Masked Image Modeling (MIM)-based models, such as SdAE, CAE, GreenMIM, and MixAE, have explored different strategies to enhance the performance of Masked Autoencoders (MAE) by modifying prediction, loss functions, or inc…
Semantic SegmentationGrammatical Error Correction Using Pseudo Learner Corpus Considering Learner's Error Tendency
Recently, several studies have focused on improving the performance of grammatical error correction (GEC) tasks using pseudo data. However, a large amount of pseudo data are required to train an accurate GEC model. To ad…
Grammatical Error CorrectionDoubly-Robust Self-Training
Self-training is a well-established technique in semi-supervised learning, which leverages unlabeled data by generating pseudo-labels and incorporating them with a limited labeled dataset for training. The effectiveness …
Pseudo-Label Noise Suppression Techniques for Semi-Supervised Semantic Segmentation
Semi-supervised learning (SSL) can reduce the need for large labelled datasets by incorporating unlabelled data into the training. This is particularly interesting for semantic segmentation, where labelling data is very …
Pose EstimationPseudo LabelPseudo Label FilteringSemantic Segmentation+1Integrating Distribution Matching into Semi-Supervised Contrastive Learning for Labeled and Unlabeled Data
The advancement of deep learning has greatly improved supervised image classification. However, labeling data is costly, prompting research into unsupervised learning methods such as contrastive learning. In real-world s…
Contrastive LearningImage Classification