WordNet-Shp: Towards the Building of a Lexical Database for a Peruvian Minority Language

WordNet-Shp: Towards the Building of a Lexical Database for a Peruvian Minority Language Diego Magui˜no-Valencia, Arturo Oncevay-Marcos and Marco A. Sobrevilla Cabezudo Research Group on Artificial Intelligence (IA-PUCP) Departamento de Ingenier´ıa, Pontificia Universidad Cat´olica del Per´u, Lima, Per´u {dmaguino,arturo.oncevay,msobrevilla}@pucp.edu.pe Abstract WordNet-like resources are lexical databases with highly relevance information and data which could be exploited in more complex computational linguistics research and applications. The building process requires manual and automatic tasks, that could be more arduous if the language is a minority one with fewer digital resources. This study focuses in the construction of an initial WordNet database for a low-resourced and indigenous language in Peru: Shipibo-Konibo (shp). First, the stages of development from a scarce scenario (a bilingual dictionary shp-es) are described. Then, it is proposed a synset alignment method by comparing the definition glosses in the dictionary (written in Spanish) with the content of a Spanish WordNet. In this sense, word2vec similarity was the chosen metric for the proximity measure. Finally, an evaluation process is performed for the synsets, using a manually annotated Gold Standard in Shipibo-Konibo. The obtained results are promising, and this resource is expected to serve well in further applications, such as word sense disambiguation and even machine translation in the shp-es language pair. Keywords: WordNet, lexical database, minority language 1. Introduction The building of digital linguistic resources is a great sup- port for endangered languages, as they help to preserve rel- evant information and knowledge related, not only for the language itself, but also for the community whose speak it. Nevertheless, if those resources are not developed to be able for further analysis and research, they may be insufficient to assist in the preservation efforts (Berment, 2002). In that context, computational linguistics is a research area that aims to understand linguistic phenomena, in an auto- matic way, through the processing and exploiting either lin- guistic corpora or language patterns from large amounts of data. In order to achieve that goal, the corpus must be in a machine-readable format, and might include structured information and linguistic meta-data that helps to automat- ically understand patterns from the language. Among the most important lexical and structured resources, the WordNet is included (Fellbaum, 1998). This resource could be used as a thesaurus for different languages, and its exploitation might ease more complex tasks such as word sense disambiguation or even machine translation. For that reason, this article describes the building of an initial version of a WordNet for an endangered language, which faces additional problems caused by the low-density of digital resources. The language case study is Shipibo- Konibo (SHP), one of the 47 indigenous languages spo- ken in Peru, specifically in the Amazonian region and has over 23,000 speakers. (Ministerio de Educaci´on, Per´u, 2013). Like most of it peers, SHP is classified as a minority language from both a social and a computational perspec- tive (Forcada, 2006). The paper is organized as follow. Section 2 defines shortly what a WordNet is. Next, Section 3 presents works regard- …

Content truncated to 500 words