A Machine Learning-Based Coreference Detection System for OntoNotes.
CONLL Shared Task '11: Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task（2011）
摘要
In this paper, we describe the algorithms and experimental results of Brandeis University in the participation of the CoNLL Task 2011 closed track. We report the features used in our system, and describe a novel cluster-based chaining algorithm to improve performance of coreference identification. We evaluate the system using the OntoNotes data set and describe our results.
更多查看译文
关键词
Brandeis University,CoNLL Task,OntoNotes data,chaining algorithm,closed track,coreference identification,experimental result,coreference detection system
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要