A Two-Level Morphological Analyser for the Indonesian Language

A Two-Level Morphological Analyser for the Indonesian Language Femphy Pisceldo, Rahmad Mahendra & Ruli Manurung Faculty of Computer Science University of Indonesia fep40@ui.edu,rama42@ui.edu,maruli@cs.ui.ac.id I Wayan Arka Department of Linguistics Australian National University wayan.arka@anu.edu.au Abstract This paper presents our efforts at developing an Indonesian morphological analyser that pro- vides a detailed analysis of the rich affixation process1. We model Indonesian morphology us- ing a two-level morphology approach, decom- posing the process into a set of morphotactic and morphophonemic rules. These rules are modelled as a network of finite state transduc- ers and implemented using xfst and lexc. Our approach is able to handle reduplication, a non-concatenative morphological process. 1 Introduction Morphology is the study of the way that words are built up from smaller units called morphemes, the minimal meaning-bearing units in a language (Ju- rafsky, 2000). For example, the English word kind consists of a single morpheme (the root word kind) whilst the word players consists of three mor- phemes: play, -er and -s. The morphemes kind and play can stand alone as words, while affixes -er and -s must appear bound to another morpheme. By applying a set of morphological rules, we can produce not just morphemes but also other in- formation relating to the words; for example, the grammatical category of the whole word as well as the subcategorisation frame of the word if it is a verb. This process is called morphological analysis. In this respect, the value of a morphological ana- lyser would be twofold: from a theoretical (linguis- tic) viewpoint, it is a very useful tool for linguistic modelling and for testing certain analyses. On the 1 This research is part of a collaborative research project funded by ARC Discovery Grant DP0877595. other hand, from a practical viewpoint, it supports many applications, e.g. information retrieval, search engines, and machine translation, among others. There is currently some interest in developing morphological tools for the Indonesian language. In previous work, Siregar (1995) and Adriani et al. (2007) discuss the development of Indonesian stemmers that recover a root from an affixed word, implemented procedurally. However, stemmers are of limited use as they do not provide any more lin- guistic information beyond the stem. Hartono (2002) presents an initial version of a morphologi- cal analyser developed with PC-KIMMO, but un- fortunately, it does not handle reduplication, a key aspect of Indonesian morphology. The morpho- logical analyser that we are developing and that we describe here is designed to be able to handle the rich semantic, lexical and grammatical information associated with words and word formation in NLP applications. In Section 2, we first discuss Indonesian mor- phology, followed by a brief explanation of two- level morphology in Section 3. Sections 4 and 5 present our work in applying two-level morphol- ogy for the Indonesian language. Finally, Section 6 presents the results of some evaluations we carried out on our developed analyser. 2 Indonesian Language Morphology Indonesian is a variety of Malay, which belongs to the Austronesian language family (Gordon, …

Content truncated to 500 words