Building the Old Javanese Wordnet

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 2940–2946 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 2940 Building the Old Javanese Wordnet David Moeljadi, Zakariya Pamuji Aminullah Palacký University, Gadjah Mada University Olomouc, Czechia; Yogyakarta, Indonesia {davidmoeljadi, zakariya.aminullah}@gmail.com Abstract This paper discusses the construction and the ongoing development of the Old Javanese Wordnet. The words were extracted from the digitized version of the Old Javanese–English Dictionary (Zoetmulder, 1982). The wordnet is built using the ‘expansion’ approach (Vossen, 1998), leveraging on the Princeton Wordnet’s core synsets and semantic hierarchy, as well as scientific names. The main goal of our project was to produce a high quality, human-curated resource. As of December 2019, the Old Javanese Wordnet contains 2,054 concepts or synsets and 5,911 senses. It is released under a Creative Commons Attribution 4.0 International License (CC BY 4.0). We are still developing it and adding more synsets and senses. We believe that the lexical data made available by this wordnet will be useful for a variety of future uses such as the development of Modern Javanese Wordnet and many language processing tasks and linguistic research on Javanese. Keywords: Old Javanese, Kawi, wordnet, less resourced language 1. Introduction This paper discusses the process of constructing a new wordnet for Old Javanese, a language written particularly in Java Island in Indonesia between 800 AD to 1500 AD. It belongs to the Western Malayo-Polynesian branch of the Austronesian language family. Despite its importance for historical and comparative linguistics, as well as ancient history, Old Javanese remains comparatively low in digi- tal resources. To the best of our knowledge, there are some digital resources for Old Javanese such as the online Old Javanese–English Dictionary, which is a part of SEAlang projects, and Kawi Lexicon (Wojowasito and Mills, 1980). However, there is no wordnet for Old Javanese (as well as Modern Javanese). This absence of an open-source Old Ja- vanese wordnet fed our motivations to build it. We aim to build a machine readable resources for Old Ja- vanese: providing a wordnet for the language, which will also be the first wordnet for the Javanese branch of West- ern Malayo-Polynesian. We would like our Old Javanese Wordnet to support many Natural Language Processing (NLP) tasks, such as machine translation and grammar en- gineering; at the same time, to support the study of linguis- tics, such as historical linguistics, lexical semantics, and verb subcategorization. In addition, we would like to lever- age it to build a wordnet for Modern Javanese. 2. Old Javanese Old Javanese (or Kawi, ISO 639-2: kaw) is the first stage of the Javanese language which has been recorded in writing for more than 600 years. The oldest inscription written in Old Javanese is dated 25 March 804 AD and Old Javanese texts and traditions continue to flourish until the present in religious and social practice, as well as in artistic and ritual contexts (Creese, 2001). It is a Western Malayo-Polynesian language of …

Content truncated to 500 words