Joint Learning for Coreference Resolution with Markov Logic.
EMNLP-CoNLL '12: Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning(2012)
摘要
Pairwise coreference resolution models must merge pairwise coreference decisions to generate final outputs. Traditional merging methods adopt different strategies such as the best-first method and enforcing the transitivity constraint, but most of these methods are used independently of the pairwise learning methods as an isolated inference procedure at the end. We propose a joint learning model which combines pairwise classification and mention clustering with Markov logic. Experimental results show that our joint learning system outperforms independent learning systems. Our system gives a better performance than all the learning-based systems from the CoNLL-2011 shared task on the same dataset. Compared with the best system from CoNLL-2011, which employs a rule-based method, our system shows competitive performance.
更多查看译文
关键词
best system,independent learning system,joint learning model,joint learning system,learning-based system,pairwise classification,pairwise coreference decision,CoNLL-2011 shared task,Pairwise coreference resolution model,best-first method,Markov logic
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络