The Grammatical Function Analysis between Korean Adnoun Clause and Noun Phrase by Using Support Vector Machines

The Grammatical Function Analysis between Korean Adnoun Clause and Noun Phrase by Using Support Vector Machines Songwook Lee Dept. of Computer Science, Sogang University 1 Sinsu-dong, Mapo-gu Seoul, Korea 121-742 gospelo@nlprep.sogang.ac.kr Tae-Yeoub Jang Dept. of English, Hankuk University of Foreign Studies 270, Imun-dong, Dongdaemun-gu, Seoul, Korea 130-791 tae@hufs.ac.kr Jungyun Seo Dept. of Computer Science, Sogang University 1 Sinsu-dong, Mapo-gu Seoul, Korea 121-742 seojy@ccs.sogang.ac.kr Abstract This study aims to improve the performance of identifying grammatical functions between an adnoun clause and a noun phrase in Korean. The key task is to determine the relation between the two constituents in terms of such functional categories as subject, object, adverbial, and appositive. The problem is mainly caused by the fact that functional morphemes, which are considered to be crucial for identifying the relation, are frequently omitted in the noun phrases. To tackle this problem, we propose to employ the Support Vector Machines(SVM) in determining the grammatical functions. Through an experiment with a tagged corpus for training SVMs, the proposed model is found to be useful. 1 Introduction Many structural ambiguities in Korean sentences are one of the major problems in Korean syntactic analyses. Most of those ambiguities can be classified into either of two categories known as "noun phrase (NP) attachment problem" and "verb phrase (VP) attachment problem". The NP attachment problem refers to finding the VP which is the head of an NP. On the other hand, the VP attachment problem refers to finding the VP which is the head of a VP. In resolving the NP attachment problem, functional morphemes play an important role as they are the crucial elements in characterizing the grammatical function between an NP and its related VP. However, the problem is that there are many NPs that do not have such functional morphemes explicitly attached to each of them. This omission makes it difficult to identify the relation between constituents and subsequently to solve the NP attachment problem. Moreover, most Korean sentences are complex sentences, which also makes the problem more complicated. In this research, we make an attempt to solve this problem. The focus is on the analysis of the grammatical function between an NP and an embedded adnoun clause with a functional morpheme omitted. We adopt Support Vector Machines(SVM) as the device by which a given adnoun clause is analyzed as one of three relative functions (subject, object, or adverbial) or an appositive. Later in this paper (section 3), a brief description of SVM will be given. 2 Korean Adnoun Clauses and their analysis problems Adnoun clauses are very frequent in Korean sentences. In a corpus, for example, they appear as often as 18,264 times in 11,932 sentences (see section 4, for details). It means that effective analyses of adnoun clauses will directly lead to improved performance of lexical, morphological and syntactic processing by machine. In order to indicate the difficulties of the adnoun clause analysis, we need to have some basic knowledge on the structure of Korean adnoun clause formation. Thus, we will …

Content truncated to 500 words