Despite Southeast Asia’s (SEA) extraordinary linguistic and cultural diversity, the region remains significantly underrepresented in vision-language (VL) research, resulting in AI models that inadequately capture SEA cultural nuances. To fill this gap, we present SEA-VL, an open-source initiative dedicated to developing culturally relevant high-quality datasets for SEA languages. By involving contributors from SEA countries, SEA-VL ensures better cultural relevance and diversity, fostering greater inclusivity of underrepresented languages and cultural depictions in VL research. Our methodology employed three approaches: community-driven crowdsourcing with SEA contributors, automated image crawling, and synthetic image generation. We evaluated each method’s effectiveness in capturing cultural relevance. We found that image crawling achieves approximately ~85% cultural relevance while being more cost- and time-efficient than crowdsourcing, whereas synthetic image generation failed to accurately reflect SEA cultural nuances and contexts. Collectively, we gathered 1.28 million SEA culturally relevant images, more than 50 times larger than other existing datasets. This work bridges the representation gap in SEA, establishes a foundation for developing culturally aware AI systems for this region, and provides a replicable framework for addressing representation gaps in other underrepresented regions.

This study explores the ethical challenges faced by Indonesian Large Language Models (LLMs), particularly focusing on their ability to distinguish between ethical and unethical instructions. As LLMs become increasingly integrated into sensitive applications, ensuring their ethical operation is crucial. A key contribution of this study is the introduction of the Anak Baik dataset, a resource designed to enhance the ethical reasoning capabilities of Indonesian LLMs. The phrase “Anak Baik”, meaning “Good Boy”, symbolizes the ideal of ethical behavior, as a well-behaved child refrains from engaging in harmful actions. The dataset comprises instruction-response pairs in Indonesian, crafted for Supervised Fine-Tuning (SFT) tasks. It includes examples of both ethical and unethical responses to guide models in learning to generate responses that uphold moral standards. Leveraging Low-Rank Adaptation (LoRA) on models such as Komodo and Cendol shows a significant improvement in ethical decision-making processes. This enhanced performance is quantitatively validated through substantial increases in BLEU and ROUGE scores, indicating a stronger alignment with socially responsible behavior.

In this SemEval 2025 Task 11 paper, we tackled three tracks: Multi-label Emotion Detection, Emotion Intensity, and Cross-lingual Emotion Detection. Our approach harnesses diverse external corpora and robust data augmentation techniques across Spanish, English, and Arabic, enhancing both the diversity and resilience of the dataset. Instead of developing separate models for each language, we merge the data into a unified multilingual dataset, enabling our model to learn cross-lingual patterns and relationships simultaneously. Our ensemble architecture integrates the multilingual strengths of XLM-RoBERTa, a zero-shot classification capability via LLaMA 3, and a specialized pretrained model fine-tuned on English emotion classification. Notably, our system achieved strong performance, ranking 13th for Afrikaans (afr) in Track A, 13th for Amharic (amh) in Track B, and 4th for Hindi (hin) in Track C.

We present NusaCrowd, a collaborative initiative to collect and unify existing resources for Indonesian languages, including opening access to previously non-public resources. Through this initiative, we have brought together 137 datasets and 118 standardized data loaders. The quality of the datasets has been assessed manually and automatically, and their value is demonstrated through multiple experiments.NusaCrowd’s data collection enables the creation of the first zero-shot benchmarks for natural language understanding and generation in Indonesian and the local languages of Indonesia. Furthermore, NusaCrowd brings the creation of the first multilingual automatic speech recognition benchmark in Indonesian and the local languages of Indonesia. Our work strives to advance natural language processing (NLP) research for languages that are under-represented despite being widely spoken.

This paper describes our team’s submission for the Social Media Mining for Health (SMM4H) 2021 shared task. We participated in three subtasks: Classifying adverse drug effect, COVID-19 self-report, and COVID-19 symptoms. Our system is based on BERT model pre-trained on the domain-specific text. In addition, we perform data cleaning and augmentation, as well as hyperparameter optimization and model ensemble to further boost the BERT performance. We achieved the first rank in both classifying adverse drug effects and COVID-19 self-report tasks.

We describe TelU-KU models of large-scale multilingual machine translation for five Southeast Asian languages: Javanese, Indonesian, Malay, Tagalog, Tamil, and English. We explore a variation of hyperparameters of flores101_mm100_175M model using random search with 10% of datasets to improve BLEU scores of all thirty language pairs. We submitted two models, TelU-KU-175M and TelU-KU- 175M_HPO, with average BLEU scores of 12.46 and 13.19, respectively. Our models show improvement in most language pairs after optimizing the hyperparameters. We also identified three language pairs that obtained a BLEU score of more than 15 while using less than 70 sentences of the training dataset: Indonesian-Tagalog, Tagalog-Indonesian, and Malay-Tagalog.

This paper describes the participation of DBMS-KU team in the SemEval 2019 Task 9, that is, suggestion mining from online reviews and forums. To deal with this task, we explore several machine learning approaches, i.e., Random Forest (RF), Logistic Regression (LR), Multinomial Naive Bayes (MNB), Linear Support Vector Classification (LSVC), Sublinear Support Vector Classification (SSVC), Convolutional Neural Network (CNN), and Variable Length Chromosome Genetic Algorithm-Naive Bayes (VLCGA-NB). Our system obtains reasonable results of F1-Score 0.47 and 0.37 on the evaluation data in Subtask A and Subtask B, respectively. In particular, our obtained results outperform the baseline in Subtask A. Interestingly, the results seem to show that our system could perform well in classifying Non-suggestion class.

This paper presents the participation of DBMS-KU Interpolation system in WMT19 shared task, namely, Kazakh-English language pair. We examine the use of interpolation method using a different language model order. Our Interpolation system combines a direct translation with Russian as a pivot language. We use 3-gram and 5-gram language model orders to perform the language translation in this work. To reduce noise in the pivot translation process, we prune the phrase table of source-pivot and pivot-target. Our experimental results show that our Interpolation system outperforms the Baseline in terms of BLEU-cased score by +0.5 and +0.1 points in Kazakh-English and English-Kazakh, respectively. In particular, using the 5-gram language model order in our system could obtain better BLEU-cased score than utilizing the 3-gram one. Interestingly, we found that by employing the Interpolation system could reduce the perplexity score of English-Kazakh when using 3-gram language model order.