Papers with fully supervised model
Efficient Semi-supervised Consistency Training for Natural Language Understanding (2022.naacl-industry)
Copied to clipboard
| Challenge: | Manually labeled training data is expensive, noisy, and often scarce . semi-supervised learning methods can be used to improve model performance . |
| Approach: | They explore different methods for consistency training on unlabeled data . they use human paraphrasing, back-translation, and dropout to augment unlabed data. |
| Outcome: | The proposed methods outperform purely supervised learning on unlabeled data. |
Document-Level Event Argument Extraction by Conditional Generation (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing event extraction models have been limited to the sentence level . this formulation signifies a misalignment between the information seeking behavior and the informative seeking behavior. |
| Approach: | They propose a document-level neural event argument extraction model by formulating the task as conditional generation following event templates. |
| Outcome: | The proposed model achieves 7.6% F1 and 5.7% F1 over the best baseline on the document-level event extraction dataset WikiEvents and 9.3% F1 on the informative argument extraction task. |
ELLEN: Extremely Lightly Supervised Learning for Efficient Named Entity Recognition (2024.lrec-main)
Copied to clipboard
| Challenge: | Named entity recognition (NER) tasks require an amount of annotations that are unrealistic for many real-world applications. |
| Approach: | They propose a semi-supervised named entity recognition method that blends language models with linguistic rules. |
| Outcome: | The proposed method outperforms most existing semi-supervised methods under the same supervision settings commonly used in the literature. |