联合语义角色标注和指代消解

被引:6
作者
熊皓 [1 ,2 ]
刘群 [1 ]
吕雅娟 [1 ]
机构
[1] 中国科学院计算技术研究所
[2] 橙译中科信息技术有限公司
关键词
语义角色标注; 指代消解; 马尔科夫逻辑网络;
D O I
暂无
中图分类号
TP391.1 [文字信息处理];
学科分类号
081203 ; 0835 ;
摘要
语义角色标注和指代消解是自然语言处理中两个重要的基础研究任务,该文提出使用马尔科夫逻辑网络对两个任务进行联合学习推导。通过提出8条联合学习规则,在OntoNote5.0的实验中证明采用联合学习推导后,两者的标注性能都比单独标注任务有了1.6个F值的性能提升。
引用
收藏
页码:58 / 68
页数:11
相关论文
共 26 条
[1]   基于最大熵分类器的语义角色标注 [J].
刘挺 ;
车万翔 ;
李生 .
软件学报, 2007, (03) :565-573
[2]  
BLANC: Implementing the Rand index for coreference evaluation[J] . M. RECASENS,E. HOVY. &nbspNatural Language Engineering . 2010 (4)
[3]  
Markov logic networks[J] . Matthew Richardson,Pedro Domingos. &nbspMachine Learning . 2006 (1)
[4]  
The Proposition Bank: An Annotated Corpus of Semantic Roles[J] . Martha Palmer,Daniel Gildea,Paul Kingsbury. &nbspComputational Linguistics . 2005 (1)
[5]  
Conll-2012shared task:Modeling multilingual unrestricted coreference in ontonotes. Sameer Pradhan,Alessandro Moschitti,Nianwen Xue,et al. Joint Conference on EMNLP and CoNLL-Shared Task . 2012
[6]  
A model theoretic coreference scoring scheme. Marc Vilain,John Burger,John Aberdeen,et al. Proceedings of the 6th conference on Message understanding . 1995
[7]   Automatic Labeling of semantic roles [J].
Gildea, D ;
Jurafskyy, D .
COMPUTATIONAL LINGUISTICS, 2002, 28 (03) :245-288
[8]  
Relaxcor participation in conll shared task on coreference resolution. Emili Sapena,Lluis Padrdo,Jordi Turmo. Proceedings of the 15th Conference on Computational Natural Language Learning:Shared Task . 2011
[9]  
Improving machine learning approaches to coreference resolution. Vincent Ng,Claire Cardie. Proceedings of 40th Annual Meeting of the Association for Computational Linguistics . 2002
[10]  
Latent structure perceptron with feature induction for unrestricted coreference resolution. Eraldo Fernandes,et al. Joint Conference on EMNLP and CoNLL-Shared Task . 2012