Coreference Resolution
Coreference resolution, the task of identifying mentions of the same real-world entity within text, aims to improve natural language understanding by resolving ambiguities in pronoun references and other expressions. Current research focuses on enhancing model performance across diverse languages and document types, employing techniques like end-to-end neural networks, transformer-based models, and graph-based approaches to capture complex relationships between mentions. These advancements are crucial for improving various NLP applications, including question answering, summarization, and information extraction, as well as for mitigating biases in language models.
Papers
SPLICE: A Singleton-Enhanced PipeLIne for Coreference REsolution
Yilun Zhu, Siyao Peng, Sameer Pradhan, Amir Zeldes
Linear Cross-document Event Coreference Resolution with X-AMR
Shafiuddin Rehan Ahmed, George Arthur Baker, Evi Judge, Michael Regan, Kristin Wright-Bettner, Martha Palmer, James H. Martin