摘要
在FrameNet,有定的零形式识别旨在发现框架语义标注语料中需要填充的零形式框架元素,有助于篇章理解能力的提高。针对该任务,该文提出一个简单的二级流水线的有定的零形式识别方法:第一级基于规则在语义角色标注的基础上检测出语料中的零形式,第二级使用最大熵分类器预测检测出来的零形式类别,以达到有定的零形式识别的目的。实验在SemEval-2010Task 10的测试集中的结果显示,零形式检测的召回率和分类准确率分别为60.1%和53.5%,接近于评测给出的最好结果。
In FrameNet, definite null instantiation detection aims to find null instantiation of the frame elements which need to be filled in frame semantic annotation corpus, which is beneficial for text understanding. This paper proposed a simple two-stage pipeline solution to definite null instantiation recognizing： the first stage used rule-based approach to detect null instantiations in the corpus which have been semantic roles labeled, and the second stage pre diets which types the null instantiations previously detected belongs to based on maximum entropy. The results of test data from SemEval-2010 Task 10 show that the recall of null instantiation detection and the precision of null in- stantiation classification are 60.1 ~ and 53.5 ~, respectively, close to the best result of the evaluation.
出处
《中文信息学报》
CSCD
北大核心
2013年第3期107-112,126,共7页
Journal of Chinese Information Processing
基金
国家自然科学基金资助项目(60970053)
国家语委"十二五"科研规划资助(YB125-19)
山西省国际科技合作资助项目(2010081044)
山西省实验室开放基金资助(2009011059-4)
国家863计划资助项目(2006AA01Z142)
