蒙古语形容词充当的语义角色分布研究

On the Semantic Role Distribution of Mongolian Adjectives

语义角色研究属于浅层语义分析范围,是实现深层语义分析的必经之路。本文基于多层标注加工语料库,对蒙古语形容词充当的语义角色分布特征进行了计量研究。据统计,多层标注加工语料库中共有767个形容词充当了语义角色,语义角色频次范围在1一684之间,语义角色频次总数为891,语义角色分布不均匀,频次最高的语义角色是性状。通过概率分布拟合,发现蒙古语形容词充当的语义角色分布是有规律可循的,其分布符合修正的右截尾齐普夫一阿列克谢耶夫分布模型。

Semantic role research belongs to the scope of shallow semantic analysis,and is the only way to achieve deep semantic analysis.Based on the multi-layer annotation processing corpus,this paper makes a quantitative study of the semantic role distribution of Mongolian adjectives.According to statistics,there are 767 adjectives serving as semantic roles in the multi-layer annotation processing corpus,and the frequency range of semantic roles is 1-684,and the total frequency of semantic roles is 891.The distribution of semantic roles is uneven,and the semantic roles with the highest frequency are traits.Through probability distribution fitting,it is found that the semantic role distribution of Mongolian adjectives is regular,and its distribution conforms to the modified right-truncated tail aligned Puff-Alexeev distribution model.