|
|||||
|
|
| 联合语义角色标注和指代消解 | |
| 引用本文： | 熊 皓,刘 群,吕雅娟. 联合语义角色标注和指代消解[J]. 中文信息学报, 2013, 27(6): 58-69 |
| 作者姓名： | 熊 皓 刘 群 吕雅娟 |
| 作者单位： | 1. 中国科学院 计算技术研究所,北京 100190; 2. 橙译中科信息技术有限公司,北京 100010 |
| 基金项目： | 国家863计划重大项目资助(2011AA01A207) |
| 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。 |
| 关 键 词： | 语义角色标注 指代消解 马尔科夫逻辑网络 |
Joint Semantic Role Labeling and Coreference Resolution |
|
| XIONG Hao,LIU Qun,LV Yajuan. Joint Semantic Role Labeling and Coreference Resolution[J]. Journal of Chinese Information Processing, 2013, 27(6): 58-69 | |
| Authors: | XIONG Hao LIU Qun LV Yajuan |
| Affiliation: | 1. Institute of Computing Technology,Beijing 100190, China; 2. Torangetek Inc., Beijing 100010, China |
| Abstract: | Semantic Role Labeling(SRL) and Coreference Resolution(CR) play important role in natural language processing applications. In this paper, we propose 8 rules to jointly learn and inference two tasks using markov logic network. Experimental results on OntoNote5.0 show that joint learning with markov logic network significantly improve 1.6 points in term of F score both on SRL and CR towards single systems. Key wordssemantic role labeling; coreference resolution; markov logic network |
| Keywords: | semantic role labeling coreference resolution markov logic network |
| 点击此处可从《中文信息学报》浏览原始摘要信息 | |
| 点击此处可从《中文信息学报》下载全文 | |