44 citations · 67 across the 24 of their papers we have counts for
28 papers
Language Distances are Practical for Equitable Cross-Lingual Transfer
York Hay Ng, Razan Ahsan Rifandi, Aditya Khan +1
Cross-lingual transfer is strongly conditional on how the source language is chosen, but it is impractical to determine the best candidate source for every target language, especia…
Typological Feature Prediction with Large Language Models: An In-Context Learning Approach
Qianwen Wang, York Hay Ng, Aditya Khan +1
Typological features are widely used in multilingual NLP, and the prediction of such features holds downstream utility. However, existing methods to predict missing values lack int…
Dynamic Meta-Metrics: Source-Sentence Conditioned Weighting for MT Evaluation
Luke Zhang, Justin Vasselli, Aditya Khan +2
We propose Dynamic Meta-Metrics (DMM), a framework for machine translation evaluation that learns source-sentence conditioned combinations of existing metrics. Rather than relying…
OasisSimp: An Open-source Asian-English Sentence Simplification Dataset
Hannah Liu, Muxin Tian, Iqra Ali +8
Sentence simplification aims to make complex text more accessible by reducing linguistic complexity while preserving the original meaning. However, progress in this area remains li…
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…
WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines
Genta Indra Winata, Frederikus Hudi, Patrick Amadeus Irawan +48
Vision Language Models (VLMs) often struggle with culture-specific knowledge, particularly in languages other than English and in underrepresented cultural contexts. To evaluate th…
URIEL+: Enhancing Linguistic Inclusion and Usability in a Typological and Multilingual Knowledge Base
Aditya Khan, Mason Shipton, David Anugraha +5
URIEL is a knowledge base offering geographical, phylogenetic, and typological vector representations for 7970 languages. It includes distance measures between these vectors for 40…
ProxyLM: Predicting Language Model Performance on Multilingual Tasks via Proxy Models
David Anugraha, Genta Indra Winata, Chenyue Li +2
Performance prediction is a method to estimate the performance of Language Models (LMs) on various Natural Language Processing (NLP) tasks, mitigating computational costs associate…
IrokoBench: A New Benchmark for African Languages in the Age of Large Language Models
David Ifeoluwa Adelani, Jessica Ojo, Israel Abebe Azime +24
Despite the widespread adoption of Large language models (LLMs), their remarkable capabilities remain limited to a few high-resource languages. Additionally, many low-resource lang…
A Reproducibility Study on Quantifying Language Similarity: The Impact of Missing Values in the URIEL Knowledge Base
Hasti Toossi, Guo Qing Huai, Jinyu Liu +3
In the pursuit of supporting more languages around the world, tools that characterize properties of languages play a key role in expanding the existing multilingual NLP research. I…
Unlocking Parameter-Efficient Fine-Tuning for Low-Resource Language Translation
Tong Su, Xin Peng, Sarubi Thillainathan +3
Parameter-efficient fine-tuning (PEFT) methods are increasingly vital in adapting large-scale pre-trained language models for diverse tasks, offering a balance between adaptability…
Predicting Machine Translation Performance on Low-Resource Languages: The Role of Domain Similarity
Eric Khiu, Hasti Toossi, David Anugraha +6
Fine-tuning and testing a multilingual large language model is expensive and challenging for low-resource languages (LRLs). While previous studies have predicted the performance of…
Leveraging Auxiliary Domain Parallel Data in Intermediate Task Fine-tuning for Low-resource Translation
Shravan Nayak, Surangika Ranathunga, Sarubi Thillainathan +6
NMT systems trained on Pre-trained Multilingual Sequence-Sequence (PMSS) models flounder when sufficient amounts of parallel data is not available for fine-tuning. This specificall…