Analyzer to Identify Phrases and the Functional Roles in Sentences: Its Architectural Aspects

Analyzer to Identify Phrases and the Functional Roles in Sentences: Its Architectural Aspects∗ Yukiko Sasaki Alam Department of Digital Media, Hosei University 3-7-2 Kajino-cho, Koganei, Tokyo 184-8584, Japan sasaki@hosei.ac.jp Abstract. This paper presents the architectural aspects of the phrase analyzer that attempts to recognize phrases and identify the functional roles in the sentences in formal Japanese documents. Since the object of interest is a phrase, the current system, designed in an object-oriented architecture, contains the Phrase class, and makes use of the linguistic generalization about languages with Case markers that a phrase, whether a noun phrase, a verb phrase, a postposition (or preposition) phrase or a clause phrase, can be separated into the content and the function components. Without a dictionary, and drawing on the orthographic information on the words to parse, it also contains a class that identifies the types of characters, a class representing grammar, and a class playing the role of a controller. The system has a simple and intuitive structure, externally and internally, and therefore is easy to modify and extend. Keywords: Phrase analyzer, Morphological analyzer, Functional roles of phrases, Japanese 1. Introduction This paper describes the architecture of the small-scale phrase analyzer that attempts to parse into phrases texts transcribed wherever applicable in Joyo Kanji (frequently used Chinese characters), and to identify the functional roles of the phrases in the sentences. Such texts are found in articles in newspapers, professional magazines and journals, and government documents. Because there are no spaces between words in Japanese texts, word-breaking is not a straight-forward task. In the past there have been several morphological analyzers: notably, Juman (Kurohashi and Nagao, 2003) and Chasen (Matsumoto et al., 2000). The two large-scale analyzers parse Japanese texts into morphemes such as prefixes, suffixes, inflections, Case markers, particles and the components of compound words. The main task of the proposed system, however, is to parse sentences into phrases (not morphemes), and identify the functional roles of the phrases, because the objective is to understand sentences in terms of the functional roles of the phrases. The second difference of the current system is that it is not intended to parse into phrases per se, but to identify the functional roles of the phrases. To recognize phrases, it resorts to a general characteristic of phrases in sentences found in formal documents. The general feature is that the component representing the content of a phrase is transcribed in Kanji (Chinese characters) or/and Katakana (phonetic characters used for transcribing words of foreign origin), and that the component expressing the function in Hiragana (phonetic characters used for transcribing words or morphemes of Japanese origin). There have been developed such morphological analyzers that exploit the orthographic difference between the content and ∗ Copyright 2007 by Yukiko Sasaki Alam 67 functional components of phrases: to name a few, Asahara (2003), Kazama (2001), Kashioka et al (1998), and Kameda (1996). All of them, unlike the current system, focus on the parsing into morphemes or phrases, but not on the identification of …

Content truncated to 500 words