44 citations · 67 across the 24 of their papers we have counts for
12 papers · 1 filter
M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG
David Anugraha, Patrick Amadeus Irawan, Anshul Singh +2
Vision-language models (VLMs) have achieved strong performance in visual question answering (VQA), yet they remain constrained by static training data. Retrieval-Augmented Generati…
Rethinking what Matters: Effective and Robust Multilingual Realignment for Low-Resource Languages
Quang Phuoc Nguyen, David Anugraha, Felix Gaschi +2
Realignment is a promising strategy to improve cross-lingual transfer in multilingual language models. However, empirical results are mixed and often unreliable, particularly for t…
\textsc{CantoNLU}: A benchmark for Cantonese natural language understanding
Junghyun Min, York Hay Ng, Sophia Chan +2
Cantonese, although spoken by millions, remains under-resourced due to policy and diglossia. To address this scarcity of evaluation frameworks for Cantonese, we introduce \textsc{\…
Simple Additions, Substantial Gains: Expanding Scripts, Languages, and Lineage Coverage in URIEL+
Mason Shipton, York Hay Ng, Aditya Khan +4
The URIEL+ linguistic knowledge base supports multilingual research by encoding languages through geographic, genetic, and typological vectors. However, data sparsity (e.g. missing…
Modality Matching Matters: Calibrating Language Distances for Cross-Lingual Transfer in URIEL+
York Hay Ng, Aditya Khan, Xiang Lu +5
Existing linguistic knowledge bases such as URIEL+ provide valuable geographic, genetic and typological distances for cross-lingual transfer but suffer from two key limitations. Fi…
SiniticMTError: A Machine Translation Dataset with Error Annotations for Sinitic Languages
Hannah Liu, Junghyun Min, En-Shiun Annie Lee +12
Despite major advances in machine translation (MT) in recent years, progress remains limited for many low-resource languages that lack large-scale training data and linguistic reso…
MERLIN: Multi-Stage Curriculum Alignment for Multilingual Encoder-LLM Integration in Cross-Lingual Reasoning
Kosei Uemura, David Guzmán, Quang Phuoc Nguyen +3
Large language models excel in English but still struggle with complex reasoning in many low-resource languages (LRLs). Existing encoder-plus-decoder methods such as LangBridge and…
TranslationCorrect: A Unified Framework for Machine Translation Post-Editing with Predictive Error Assistance
Syed Mekael Wasti, Shou-Yi Hung, Christopher Collins +1
Machine translation (MT) post-editing and research data collection often rely on inefficient, disconnected workflows. We introduce TranslationCorrect, an integrated framework desig…
Datasheets Aren't Enough: DataRubrics for Automated Quality Metrics and Accountability
Genta Indra Winata, David Anugraha, Emmy Liu +17
High-quality datasets are fundamental to training and evaluating machine learning models, yet their creation-especially with accurate human annotations-remains a significant challe…
Beyond Vanilla Fine-Tuning: Leveraging Multistage, Multilingual, and Domain-Specific Methods for Low-Resource Machine Translation
Sarubi Thillainathan, Songchen Yuan, En-Shiun Annie Lee +2
Fine-tuning multilingual sequence-to-sequence large language models (msLLMs) has shown promise in developing neural machine translation (NMT) systems for low-resource languages (LR…
AlignFreeze: Navigating the Impact of Realignment on the Layers of Multilingual Models Across Diverse Languages
Steve Bakos, Félix Gaschi, David Guzmán +3
Realignment techniques are often employed to enhance cross-lingual transfer in multilingual language models, still, they can sometimes degrade performance in languages that differ…
INJONGO: A Multicultural Intent Detection and Slot-filling Dataset for 16 African Languages
Hao Yu, Jesujoba O. Alabi, Andiswa Bukula +19
Slot-filling and intent detection are well-established tasks in Conversational AI. However, current large-scale benchmarks for these tasks often exclude evaluations of low-resource…