Disentangling Singlish Discourse Particles with Task-Driven Representation

TL;DR

This paper introduces a computational approach to disentangle Singlish discourse particles using task-driven representation learning, enabling better understanding and translation of Singlish's pragmatic functions.

Contribution

It presents a novel method for disentangling Singlish discourse particles and applying this to improve Singlish-to-English translation.

Findings

Disentangled Singlish discourse particles effectively.

Clustered particles by pragmatic functions.

Enhanced Singlish-to-English translation performance.

Abstract

Singlish, or formally Colloquial Singapore English, is an English-based 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 and hor) with task-driven 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.