Papers with data imbalance problem
Entity Pair-guided Relation Summarization and Retrieval in LLMs for Document-level Relation Extraction (2025.findings-naacl)
Copied to clipboard
| Challenge: | Document-level relation extraction (DocRE) aims to extract relations between entities in a document. |
| Approach: | They propose an entity pair-guided relation summarization and retrieval model for DocRE . the model uses entity pairs to guide relation summaries and retrievals . |
| Outcome: | The proposed model achieves state-of-the-art (SOTA) performance on three datasets. |
The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active Learning (2023.acl-long)
Copied to clipboard
| Challenge: | Prior studies have focused on translating utterances from high-resource languages to low-resourced languages. |
| Approach: | They propose an active learning approach that exploits the strengths of both human and machine translations by iteratively adding small batches of human translations into the machine-translated training set. |
| Outcome: | The proposed approach reduces errors and bias in the translated data, resulting in higher parser accuracies than the current model trained on machine translations. |
HSCNN: A Hybrid-Siamese Convolutional Neural Network for Extremely Imbalanced Multi-label Text Classification (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to solve the data imbalance problem are limited in extremely imbalanced data. |
| Approach: | They propose a hybrid approach which adapts general networks for head categories and few-shot techniques for tail categories. |
| Outcome: | The proposed approach improves the performance of Single networks with diverse loss objectives on tail or entire categories. |
Knowledge-aware Attention Network for Medication Effectiveness Prediction (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing effectiveness prediction methods focus on one specific medicine, one specific disease, or one specific lab test, making it hard to extend to general medicines and diseases in hospital/ICU scenarios. |
| Approach: | They propose to use knowledge enhanced module to incorporate external knowledge about medications and a medical feature learning module to determine the interaction between diagnosis and medications. |
| Outcome: | The proposed model outperforms state-of-the-art methods on a public dataset showing that it significantly outperformed existing models. |
Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine Translation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to multilingual neural machine translation (MNMT) are limited in their ability to handle large amounts of data. |
| Approach: | They propose a framework which only requires target-side monolingual data and a bilingual dictionary to improve the performance of the MNMT model. |
| Outcome: | The proposed framework is more effective than baselines in long-tail and high-resource languages. |