基于任务驱动表示解构新加坡英语话语助词
Disentangling Singlish Discourse Particles with Task-Driven Representation
AI总结：
本研究提出一种任务驱动表示学习方法，通过解构新加坡英语话语助词并进行聚类与机器翻译，为理解其语用功能提供了计算方法。
摘要：
新加坡英语，即正式的 Colloquial Singapore English，是一种源自东南亚国家新加坡、以英语为基础的克里奥尔语。该语言包含来自汉语族（如汉语方言）、马来语和泰米尔语等的影响。理解新加坡英语的一项基础任务是理解其话语助词的语用功能，该语言严重依赖这些助词来传达意义。本研究通过任务驱动表示学习，为解构新加坡英语话语助词（lah、meh 和 hor）提供了初步尝试。解构后，我们对这些话语助词进行聚类以区分其语用功能，并执行新加坡英语到英语的机器翻译。我们的工作为理解新加坡英语话语助词提供了一种计算方法，并为深入理解该语言及其用法开辟了途径。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
