Disentangling Singlish Discourse Particles with Task-Driven Representation
Linus Tze En Foo, Lynnette Hui Xian Ng · 2024
Singlish, or formally Colloquial Singapore English, is an Englishbased creole language originating from the SouthEast Asian country Singapore.The language contains influences from Sinitic languages such as Chinese dialects, Malay, Tamil and so forth.A fundamental task to understanding Singlish is to first understand the pragmatic functions of its discourse particles, upon which Singlish relies heavily to convey meaning.This work offers a preliminary effort to disentangle the Singlish discourse particles lah, meh, hor with taskdriven representation learning.After disentanglement, we cluster these discourse particles to differentiate their pragmatic functions, and perform Singlish-to-English machine translation.Our work provides a computational method to understanding Singlish discourse particles, and opens avenues towards a deeper comprehension of the language and its usage.