Singlish Where Got Rules One? Constructing a Computational Grammar for Singlish

Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), pages 5243–5250 Marseille, 20-25 June 2022 © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0 5243 Singlish Where Got Rules One? Constructing a Computational Grammar for Singlish Chow Siew Yeng and Francis Bond Nanyang Technological University, School of Humanities {siewyeng001, fcbond}@ntu.edu.sg Abstract Singlish is a variety of English spoken in Singapore. In this paper, we share some of its grammar features and how they are implemented in the construction of a computational grammar of Singlish as a branch of English grammar. New rules were created and existing ones from standard English grammar of the English Resource Grammar (ERG) were changed in this branch to cater to how Singlish works. In addition, Singlish lexicon was added into the grammar together with some new lexical types. We used Head-driven Phrase Structure Grammar (HPSG) as the framework for this project of creating a working computational grammar. As part of building the language resource, we also collected and formatted some data from the internet to create a test suite for Singlish. Finally, the computational grammar was tested against a set of gold standard trees and compared with the standard English grammar to find out how well the grammar fares in analysing Singlish. Keywords: Head-driven Phrase Structure Grammar, Computational Grammar, Singlish, Parsing 1. Introduction Singlish (also known as Colloquial Singapore English) is a variety of English spoken in Singapore which con- tains many non-standard features. This is shown in the example sentence taken from Wiktionary1 in (1). The first gloss line indicates the origin language of the word with M, H and E standing for Malay, Hokkien and En- glish respectively. (1) Wah lau, M/H EXPL Eyou Edamn H‘gian peng’. greedy ‘Damn! You are very greedy.’ The variety has been widely researched in terms of pho- netics, sociolinguistics and syntax (Wee, 2008; Cav- allaro et al., 2014; Alsagoff, 2010; Ansaldo, 2010). Yet, the legitimacy of this variety has not been as well recognised locally. The use of Singlish has been actively discouraged by politicians during offi- cial speeches (Lim, 2009) and the Speak Good English Movement as it is viewed to be ‘broken English’. The official campaign was based on the idea that Singlish negatively impacts the image of its speakers and is harmful towards the country’s international standing. There has been a belief that there is only one ‘right’ way of speaking English and standard English had to be chosen over Singlish (Tan, 2017). The project has been motivated in part to show how this is indeed a structured variety with proper unique features. Thus, in this paper, we write about the differ- ent aspects including rules of this new computational grammar of Singlish. This title can be roughly translated as “Singlish has rules?!”. One is an emphatic particle. 1https://en.wiktionary.org/wiki/gian_ peng The next section briefly introduces Singlish and the formal grammar framework used - Head-driven Phrase Structure Grammar (HPSG). In the following sections, we will elaborate on various features of Singlish and …

Content truncated to 500 words