Papers with data imbalance problem

5 papers
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations