Software and Toolbox

  • RejSumm: a toolbox with rejection learning and inference models for hallucination reduction in text summarization.

  • EntFA: a toolbox for hallucinated entity detection in text generation.

  • FactCorr: a toolbox for post-processing scripts that directly edit text summarization outputs for factual error reduction.

  • HipoRank: unsupervised and extractive long document summarization model with hierarchical and positional information.

  • EditNTS an edit-based method for text and sentence simplification.

  • BanditSum an extractive summarization algorithm trained with reinforcement learning with the setup of contextual multi-armed bandits.

  • HierClass a deep hierarchical neural attention-based classifier for hierarchical taxonomy datasets.

Dataset

  • FacetSum: a dataset for structured scientific document summarization. It comprises 60,024 scientific articles from Emerald journals, each with a structured abstract that summarizes the purpose, method, findings, and value.

  • Multi-XScience: a large-scale dataset for extreme multi-document summarization of scientific articles.

Please send me email if you find bugs or have comments!

Yue Dong
Yue Dong
Assistant Professor

Yue Dong is an assistant professor of computer science and engineering at the University of California Riverside. Her research interests include natural language processing, machine learning, and artificial intelligence. She leads the Natural Language Processing group, which develops natural language understanding and generation systems that are controllable, trustworthy, and efficient.