# Disentangling Singlish Discourse Particles with Task-Driven Representation

arXiv: https://arxiv.org/abs/2409.20366 · HTML: https://mlsanity.com/paper/2409.20366/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 26 references that are in the map.
- First posted on arXiv 30 Sep 2024.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla](https://mlsanity.com/paper/2101.00204/) (2021)
- [Extending Multilingual BERT to Low-Resource Languages](https://mlsanity.com/paper/2004.13640/) (2020)
- [Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese](https://mlsanity.com/paper/2205.10517/) (2022)
- [Can You Learn Semantics Through Next-Word Prediction? The Case of Entailment](https://mlsanity.com/paper/2402.13956/) (2024)
- [Extremely low-resource machine translation for closely related languages](https://mlsanity.com/paper/2105.13065/) (2021)

## Built on by (most cited first, 5 of 5)

- [LionGuard 2: Building Lightweight, Data-Efficient & Localised Multilingual Content Moderators](https://mlsanity.com/paper/2507.15339/) (2025)
- [What talking you?: Translating Code-Mixed Messaging Texts to English](https://mlsanity.com/paper/2411.05253/) (2024)
- [Limpeh ga li gong: Challenges in Singlish Annotations](https://mlsanity.com/paper/2410.16156/) (2024)
- [Disentangling Codemixing in Chats: The NUS ABC Codemixed Corpus](https://mlsanity.com/paper/2506.00332/) (2025)
- [Stylistic Evolution and LLM Neutrality in Singlish Language](https://mlsanity.com/paper/2601.06580/) (2026)

## Abstract (arXiv)

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.