Papers with data imbalance

13 papers
Leveraging Hierarchical Category Knowledge for Data-Imbalanced Multi-Label Diagnostic Text Understanding (D19-62)

Copied to clipboard

Challenge: Existing work on automatic diagnosis prediction has considered the output labels independently, so that the codes with few samples are difficult to learn.
Approach: They propose to leverage domain knowledge to predict diagnostic codes given the descriptive present illness in electronic health records by leveraging hierarchical category knowledge.
Outcome: The proposed model can efficiently utilize category knowledge and provide informative cues to improve the top-ranked diagnostic codes which is better than the prior state-of-the-art.
Adaptive Ranking-based Sample Selection for Weakly Supervised Class-imbalanced Text Classification (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to synthesize training labels with labeling rules ignore data imbalance issue . weak supervision paradigm is often used to reduce human efforts to produce training labels inexpensively.
Approach: They propose a model-agnostic framework to alleviate the data imbalance issue in the weak supervision paradigm by combining labeling rules with a probabilistic margin score.
Outcome: The proposed framework outperforms the state-of-the-art imbalanced learning and WS methods on four text classification datasets with four different imbalance ratios.
SharpSeq: Empowering Continual Event Detection through Sharpness-Aware Sequential-task Learning (2024.naacl-long)

Copied to clipboard

Challenge: Existing methods for continual event detection suffer from catastrophic forgetting . a novel continual learning paradigm leveraging sharpness-aware minimization is needed .
Approach: They propose a continual learning paradigm that leverages sharpness-aware minimization and a generative model to balance training data distribution.
Outcome: The proposed approach outperforms existing methods on real-world datasets.
Reinforcement Learning with Imbalanced Dataset for Data-to-Text Medical Report Generation (2020.findings-emnlp)

Copied to clipboard

Challenge: Medical datasets are imbalanced in their finding labels because incidence rates differ among diseases . authors propose a novel reinforcement learning method with a reconstructor to improve clinical correctness of generated reports.
Approach: They propose a reinforcement learning method with a reconstructor to improve clinical correctness of generated reports.
Outcome: The proposed method improves clinical correctness of generated reports . it also trains the model on infrequent findings .
CEPT: A Contrast-Enhanced Prompt-Tuning Framework for Emotion Recognition in Conversation (2024.lrec-main)

Copied to clipboard

Challenge: Emotion recognition in conversation research suffers from data imbalance and the presence of similar linguistic expressions for different emotions.
Approach: They propose a Contrast-Enhanced Prompt-Tuning framework that transforms an ERC task into a Masked Language Modeling task and generates the emotion for each utterance in the conversation.
Outcome: The proposed framework outperforms the state-of-the-art methods on all three benchmark datasets and excels in recognizing minority emotions.
Bi-Drop: Enhancing Fine-tuning Generalization via Synchronous sub-net Estimation and Optimization (2023.findings-emnlp)

Copied to clipboard

Challenge: Pretrained language models can be fine-tuned on limited training data, which can overfit and thus diminish performance.
Approach: They propose a fine-tuning strategy that selectively updates model parameters using gradients from various sub-nets dynamically generated by dropout.
Outcome: The proposed method outperforms existing methods on the GLUE benchmark and exhibits excellent generalization ability and robustness for domain transfer, data imbalance, and low-resource scenarios.
Curriculum Learning Meets Directed Acyclic Graph for Multimodal Emotion Recognition (2024.lrec-main)

Copied to clipboard

Challenge: Existing models for multimodal Emotion Recognition in conversation (ERC) use text as the main modality for emotion recognition.
Approach: They propose a Directed Acyclic Graph (DAG) approach that integrates textual, acoustic, and visual features within a unified framework.
Outcome: The proposed model outperforms baseline models on the IEMOCAP and MELD datasets.
UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity Mixture-of-Experts (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in unified multimodal models indicate a clear trend towards comprehensive content generation.
Approach: They propose a unified speech and music generation model built upon a novel framework . they propose specialized MoE architectures and curated training strategies to tackle data imbalances .
Outcome: The proposed model achieves state-of-the-art performance on major speech and music generation benchmarks.
Proactive Assistant Dialogue Generation from Streaming Egocentric Videos (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in conversational AI have been substantial, but developing real-time tasks guidance systems remains a challenge.
Approach: They propose a data curation pipeline that synthesizes dialogues from annotated egocentric videos and a suite of automatic evaluation metrics that validated through extensive human studies.
Outcome: The proposed framework synthesizes dialogues from annotated egocentric videos and validates them through extensive human studies.
Re-weighting Tokens: A Simple and Effective Active Learning Strategy for Named Entity Recognition (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing active learning approaches focus on information-rich sequences, reducing the need for expert annotation.
Approach: They propose a re-weighting-based active learning strategy that assigns dynamic weights to individual tokens.
Outcome: The proposed strategy improves on multiple corpora and validates its effectiveness.
LAMBDA: Large Language Model-Based Data Augmentation for Multi-Modal Machine Translation (2024.findings-emnlp)

Copied to clipboard

Challenge: Multi-modal machine translation methods are underperforming compared to pre-trained models due to lack of triplet training data.
Approach: They propose a multi-modal machine translation method that integrates images and visual modality to enhance language understanding.
Outcome: The proposed method can enrich the original samples and expand the dataset without requiring external images and text.
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.
Typology-Guided Adaptation in Multilingual Models (2025.acl-long)

Copied to clipboard

Challenge: Multilingual models often treat language diversity as a problem of data imbalance, overlooking structural variation.
Approach: They propose a typologically grounded metric that quantifies how strongly a language relies on morphology for noun classification.
Outcome: The proposed model outperforms baseline models on 10 Bantu languages . it improves Swahili accuracy by 14 points while maintaining performance on morphology-rich languages like Zulu .

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