A Japanese Predicate Argument Structure Analysis using Decision Lists

Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 523–532, Honolulu, October 2008. c⃝2008 Association for Computational Linguistics A Japanese Predicate Argument Structure Analysis using Decision Lists Hirotoshi Taira, Sanae Fujita, Masaaki Nagata NTT Communication Science Laboratories 2-4, Hikaridai, Seika-cho, Keihanna Science City, Kyoto 619-0237, Japan {{taira,sanae}@cslab.kecl, nagata.masaaki@lab}.ntt.co.jp Abstract This paper describes a new automatic method for Japanese predicate argument structure analysis. The method learns relevant features to assign case roles to the argument of the tar- get predicate using the features of the words located closest to the target predicate under various constraints such as dependency types, words, semantic categories, parts of speech, functional words and predicate voices. We constructed decision lists in which these fea- tures were sorted by their learned weights. Us- ing our method, we integrated the tasks of se- mantic role labeling and zero-pronoun iden- tification, and achieved a 17% improvement compared with a baseline method in a sen- tence level performance analysis. 1 Introduction Recently, predicate argument structure analysis has attracted the attention of researchers because this information can increase the precision of text pro- cessing tasks, such as machine translation, informa- tion extraction (Hirschman et al., 1999), question answering (Narayanan and Harabagiu, 2004) (Shen and Lapata, 2007), and summarization (Melli et al., 2005). In English predicate argument structure analysis, large corpora such as FrameNet (Fillmore et al., 2001), PropBank (Palmer et al., 2005) and NomBank (Meyers et al., 2004) have been created and utilized. Recently, the GDA Corpus (Hashida, 2005), Kyoto Text Corpus Ver.4.0 (Kawahara et al., 2002) and NAIST Text Corpus (Iida et al., 2007) were constructed in Japanese, and these corpora have become the target of an automatic Japanese predicate argument structure analysis system. We conducted Japanese predicate argument structure (PAS) analysis for the NAIST Text Corpus, which is the largest of these three corpora, and, as far as we know, this is the first time PAS analysis has been conducted for whole articles of the corpus. The NAIST Text Corpus has the following char- acteristics, i) semantic roles for both predicates and event nouns are annotated in the corpus, ii) three ma- jor case roles,1 namely the ga, wo and ni-cases in Japanese are annotated for the base form of pred- icates and event nouns, iii) both the case roles in sentences containing the target predicates and those outside the sentences (zero-pronouns) are annotated, and iv) coreference relations are also annotated. As regards i), recently there has been an increase in the number of papers dealing with nominalized predicates (Pradhan et al., 2004) (Jiang and Ng, 2006) (Xue, 2006) (Liu and Ng, 2007). For exam- ple, ‘trip’ in the sentence “During my trip to Italy, I met him.” refers not only to the event “I met him” but also to the event “I traveled to Italy.” As in this example, nouns sometimes have argument structures referring to an event. Such nouns are called event nouns (Komachi et al., 2007) in the NAIST Text Corpus. At the …

Content truncated to 500 words