Related papers: IndoRobusta: Towards Robustness Against Diverse Co…

Code-mixing is the practice of using two or more languages in a single sentence, which often occurs in multilingual communities such as India where people commonly speak multiple languages. Classic NLP tools, trained on monolingual data,…

Indonesian language is spoken by almost 200 million people and is the 10th most spoken language in the world, but it is under-represented in NLP (Natural Language Processing) research. A sparsity of language resources has hampered previous…

We investigate the robustness of Whisper-based automatic speech recognition (ASR) models for two major Indonesian regional languages: Javanese and Sundanese. While recent work has demonstrated strong ASR performance under clean conditions,…

While pixel-based language modeling aims to bypass the sub-word tokenization bottleneck by rendering text as images, recent multimodal variants such as DualGPT reintroduce text tokenizers to improve autoregressive performance. We…

Indonesian is an agglutinative language since it has a compounding process of word-formation. Therefore, the translation model of this language requires a mechanism that is even lower than the word level, referred to as the sub-word level.…

In this paper, we investigate the transferability of pre-trained language models to low-resource Indonesian local languages through the task of sentiment analysis. We evaluate both zero-shot performance and adapter-based transfer on ten…

At the center of the underlying issues that halt Indonesian natural language processing (NLP) research advancement, we find data scarcity. Resources in Indonesian languages, especially the local ones, are extremely scarce and…

Indonesia is one of the most diverse countries linguistically. However, despite this linguistic diversity, Indonesian languages remain underrepresented in Natural Language Processing (NLP) research and technologies. In the past two years,…

We present COPAL-ID, a novel, public Indonesian language common sense reasoning dataset. Unlike the previous Indonesian COPA dataset (XCOPA-ID), COPAL-ID incorporates Indonesian local and cultural nuances, and therefore, provides a more…

Tokenization constitutes a fundamental stage in Large Language Model (LLM) processing; however, subword-based tokenization methods optimized on English-dominant corpora may produce token fragmentation misaligned with the linguistic…

There is an emerging effort to develop NLP for Indonesias 700+ local languages, but progress remains costly due to the need for direct engagement with native speakers. However, it is unclear what these language communities truly need from…

Although LLMs have attained significant success in high-resource languages, their capacity in low-resource linguistic environments like Kannada and Arabic is not yet fully understood. This work benchmarking the performance of multilingual…

Social bias in language models can potentially exacerbate social inequalities. Despite it having garnered wide attention, most research focuses on English data. In a low-resource scenario, the models often perform worse due to insufficient…

Multilingualism refers to the high degree of proficiency in two or more languages in the written and oral communication modes. It often results in language mixing, a.k.a. code-mixing, when a multilingual speaker switches between multiple…

Code-mixing is a well-studied linguistic phenomenon that occurs when two or more languages are mixed in text or speech. Several studies have been conducted on building datasets and performing downstream NLP tasks on code-mixed data.…

Code-switching is the use of more than one language in the same conversation or utterance. Recently, multilingual contextual embedding models, trained on multiple monolingual corpora, have shown promising results on cross-lingual and…

BERT and IndoBERT have achieved impressive performance in several NLP tasks. There has been several investigation on its adaption in specialized domains especially for English language. We focus on financial domain and Indonesian language,…

Figurative language permeates human communication, but at the same time is relatively understudied in NLP. Datasets have been created in English to accelerate progress towards measuring and improving figurative language processing in…

Over 200 million people speak Indonesian, yet the language remains significantly underrepresented in preference-based research for large language models (LLMs). Most existing multilingual datasets are derived from English translations,…

An ideal speech recognition model has the capability to transcribe speech accurately under various characteristics of speech signals, such as speaking style (read and spontaneous), speech context (formal and informal), and background noise…