Wei Fan

On the Generation of Medical Question-Answer Pairs

2018 · arXiv (Cornell University)

Question answering (QA) has achieved promising progress recently. However, answering a question in real-world scenarios like the medical domain is still challenging, due to the requirement of external knowledge and the insufficient quantity of high-quality …

Multiplex Graph Neural Network for Extractive Text Summarization

2021 · arXiv (Cornell University)

Extractive text summarization aims at extracting the most representative sentences from a given document as its summary. To extract a good summary from a long text document, sentence embedding plays an important role. Recent studies …

A New Safe-Level Enabled Borderline-SMOTE for Condition Recognition of Imbalanced Dataset

2023 · IEEE Transactions on Instrumentation and Measurement

Machine learning-based classification strategy has been successfully applied in actual industrial monitoring but it is often hindered when the data set is imbalanced. Technically, the misclassification phenomenon, as a serious performance degradation of generalisation ability, …

AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation

2024 · arXiv (Cornell University)

Abstraction ability is crucial in human intelligence, which can also benefit various tasks in NLP study. Existing work shows that LLMs are deficient in abstract ability, and how to improve it remains unexplored. In this …

GCFL: A Gradient Correction-based Federated Learning Framework for Privacy-preserving CPSS

2025 · arXiv (Cornell University)

Federated learning, as a distributed architecture, shows great promise for applications in Cyber-Physical-Social Systems (CPSS). In order to mitigate the privacy risks inherent in CPSS, the integration of differential privacy with federated learning has attracted …

Joint Slot Filling and Intent Detection via Capsule Neural Networks

2019

Being able to recognize words as slots and detect the intent of an utterance has been a keen issue in natural language understanding. The existing works either treat slot filling and intent detection separately in …

U-BERT: Pre-training User Representations for Improved Recommendation

2021 · Proceedings of the AAAI Conference on Artificial Intelligence

Learning user representation is a critical task for recommendation systems as it can encode user preference for personalized services. User representation is generally learned from behavior data, such as clicking interactions and review comments. However, …