Unified Semantic Role Labeling for Verbal and Nominal Predicates in the Chinese Language
Unified Semantic Role Labeling for Verbal and Nominal Predicates in the Chinese Language
复制标题
DOI：
10.1145/2002980.2002983
复制
发表时间：
2011-09
期刊：
影响因子：
--
通讯作者：
Junhui Li;Guodong Zhou
中科院分区：
文献类型：
--
作者：
Junhui Li;Guodong Zhou
本文探讨了汉语中动词和名词谓词的统一语义角色标签（SRL）。这是通过在统一框架中考虑动词和名词谓词的 SRL 来完成的。首先，除了那些广泛使用的特征之外，我们分别系统地研究了言语 SRL 和名义 SRL 的各种特征。然后，我们利用各种言语证据进一步提高名义 SRL 的性能，即合并来自言语谓词的训练实例，并整合来自言语谓词的 SRL 的各种特征。最后，我们解决自动谓词识别的问题，这对于名义 SRL 至关重要。对中国 PropBank 和中国 NomBank 的评估表明，我们的统一方法显着提高了性能，特别是名义 SRL 的性能。据我们所知，这是第一个在中国 PropBank 和 NomBank 上报告的统一口头和名义 SRL 的工作。
This article explores unified semantic role labeling (SRL) for both verbal and nominal predicates in the Chinese language. This is done by considering SRL for both verbal and nominal predicates in a unified framework. First, we systematically examine various kinds of features for verbal SRL and nominal SRL, respectively, besides those widely used ones. Then we further improve the performance of nominal SRL with various kinds of verbal evidence, that is, merging the training instances from verbal predicates and integrating various kinds of features derived from SRL for verbal predicates. Finally, we address the issue of automatic predicate recognition, which is essential for nominal SRL. Evaluation on Chinese PropBank and Chinese NomBank shows that our unified approach significantly improves the performance, in particular that of nominal SRL. To the best of our knowledge, this is the first reported work of unified verbal and nominal SRL on Chinese PropBank and NomBank.