Dependency Parsing for Traditional Mongolian

Abstract

Dependency parsing has become increasingly popular in natural language processing in recent years. Nevertheless, dependency parsing focused on Tradition Mongolian has not attracted much attention. We investigate it with Maximum Spanning Tree (MST) based model on Traditional Mongolian dependency tree bank (TMDT). This paper briefly introduces Traditional Mongolian along with TMDT, and discusses the details of MST. Much emphasis is placed on the performance comparisons among eight kinds of features and their combinations in order to find a suitable feature representation. Evaluation result shows that the combination of Basic Unigram Features, Basic Bi-gram Features and C-C Sibling Features obtains the best performance. Our work establishes a baseline for dependency parsing of Traditional Mongolian.