60 citations · 119 across the 36 of their papers we have counts for
41 papers
Math2Visual-X: A Modular Framework for Pedagogically Aligned Lower-Primary Math Visuals Generation
H. D. E. Maduranga, S. K. Munasinghe, K. P. T. I. Weerasekara +2
Visual representations can help lower-primary learners understand Math Word Problems, but generating classroom-usable visuals remains difficult. Existing symbolic systems are contr…
Confident but Wrong: A Constrained Decoding Diagnostic for Low-Resource Automatic Post-Editing
Isuru Wijesiri, Nisansa de Silva, Kavindu Warnakulasuriya +2
Automatic Post-Editing (APE) for low-resource languages (LRLs) often fails to improve Machine Translation (MT), and the score alone cannot say why: whether more training would help…
EnSiTa - A Trilingual Multi-Domain Parallel Dataset and Benchmark for Domain-Specific Machine Translation
Surangika Ranathunga, Nisansa de Silva, Aloka Fernando +8
Machine Translation (MT) for low-resource languages remains far behind that of high-resource languages, and the gap is widest in specialised domains, where parallel data is scarce…
Georeferencing Non-Gazetteered Place Names using Biological Specimen Records
Aneesha Fernando, Surangika Ranathunga, Kristin Stock +2
Biological specimen records collected by natural history institutions constitute a rich source of temporal geographic knowledge, capturing biodiversity information about regional l…
LKValues: Aligning Large Language Models with Sri Lankan Societal Values
Nethmi Muthugala, Supryadi, Surangika Ranathunga +7
Value alignment of Large Language Models (LLMs) has been shown to be culturally biased toward Western norms. This results in the mishandling of local values in multilingual societi…
Which LoRA? An Empirical Study on the Effectiveness of LoRA Techniques During Multilingual Instruction Tuning
Thamali Wijewardhana, Napoleon H. Reyes, Surangika Ranathunga
We investigate whether commonly available LoRA variants have an advantage over basic LoRA in multilingual instruction tuning. Experiments involving LoRA and four other variants on…
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…
Sinhala Physical Common Sense Reasoning Dataset for Global PIQA
Nisansa de Silva, Surangika Ranathunga
This paper presents the first-ever Sinhala physical common sense reasoning dataset created as part of Global PIQA. It contains 110 human-created and verified data samples, where ea…
Forecasting Commencing Enrolments Under Data Sparsity: A Zero-Shot Time Series Foundation Models Framework for Higher Education Planning
Jittarin Jetwiriyanon, Teo Susnjak, Surangika Ranathunga
Effective resource allocation in higher education depends on reliable enrolment forecasts, yet institutional planners frequently face data series disrupted by structural shifts. Th…
Georeferencing complex relative locality descriptions with large language models
Aneesha Fernando, Surangika Ranathunga, Kristin Stock +2
Georeferencing text documents has typically relied on either gazetteer-based methods to assign geographic coordinates to place names, or on language modelling approaches that assoc…
LMSpell: Spell Correction with Pre-Trained Language Models
Akesh Gunathilake, Nadil Karunarathna, Tharusha Bandaranayake +3
Spell correction is still a challenging problem for many languages, especially low-resource languages (LRLs). While pre-trained language models (PLMs) have been employed for spell…
Extracting Disaster Impacts and Impact Related Locations in Social Media Posts Using Large Language Models
Sameeah Noreen Hameed, Surangika Ranathunga, Raj Prasanna +2
Large-scale disasters can often result in catastrophic consequences on people and infrastructure. Situation awareness about such disaster impacts generated by authoritative data fr…
Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures
Tyler A. Chang, Catherine Arnett, Abdelrahman Sadallah +377
To date, there exist almost no culturally-specific evaluation benchmarks for large language models (LLMs) that cover a large number of languages and cultures. In this paper, we pre…
Generalisation Bounds of Zero-Shot Economic Forecasting using Time Series Foundation Models
Jittarin Jetwiriyanon, Teo Susnjak, Surangika Ranathunga
This study investigates zero-shot forecasting capabilities of Time Series Foundation Models (TSFMs) for macroeconomic indicators. We apply TSFMs to forecasting economic indicators…
SinLlama -- A Large Language Model for Sinhala
H. W. K. Aravinda, Rashad Sirajudeen, Samith Karunathilake +3
Low-resource languages such as Sinhala are often overlooked by open-source Large Language Models (LLMs). In this research, we extend an existing multilingual LLM (Llama-3-8B) to be…
Utilizing Multilingual Encoders to Improve Large Language Models for Low-Resource Languages
Imalsha Puranegedara, Themira Chathumina, Nisal Ranathunga +3
Large Language Models (LLMs) excel in English, but their performance degrades significantly on low-resource languages (LRLs) due to English-centric training. While methods like Lan…
Leveraging Synthetic Data for Question Answering with Multilingual LLMs in the Agricultural Domain
Rishemjit Kaur, Arshdeep Singh Bhankhar, Jashanpreet Singh Salh +6
Enabling farmers to access accurate agriculture-related information in their native languages in a timely manner is crucial for the success of the agriculture field. Publicly avail…
Elementary Math Word Problem Generation using Large Language Models
Nimesh Ariyarathne, Harshani Bandara, Yasith Heshan +9
Mathematics is often perceived as a complex subject by students, leading to high failure rates in exams. To improve Mathematics skills, it is important to provide sample questions…
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…
A Framework to Assess Multilingual Vulnerabilities of LLMs
Likai Tang, Niruth Bogahawatta, Yasod Ginige +4
Large Language Models (LLMs) are acquiring a wider range of capabilities, including understanding and responding in multiple languages. While they undergo safety training to preven…
Improving the quality of Web-mined Parallel Corpora of Low-Resource Languages using Debiasing Heuristics
Aloka Fernando, Nisansa de Silva, Menan Velyuthan +2
Parallel Data Curation (PDC) techniques aim to filter out noisy parallel sentences from web-mined corpora. Ranking sentence pairs using similarity scores on sentence embeddings der…
Linguistic Entity Masking to Improve Cross-Lingual Representation of Multilingual Language Models for Low-Resource Languages
Aloka Fernando, Surangika Ranathunga
Multilingual Pre-trained Language models (multiPLMs), trained on the Masked Language Modelling (MLM) objective are commonly being used for cross-lingual tasks such as bitext mining…
Sinhala Transliteration: A Comparative Analysis Between Rule-based and Seq2Seq Approaches
Yomal De Mel, Kasun Wickramasinghe, Nisansa de Silva +1
Due to reasons of convenience and lack of tech literacy, transliteration (i.e., Romanizing native scripts instead of using localization tools) is eminently prevalent in the context…
Unsupervised Bilingual Lexicon Induction for Low Resource Languages
Charitha Rathnayake, P. R. S. Thilakarathna, Uthpala Nethmini +2
Bilingual lexicons play a crucial role in various Natural Language Processing tasks. However, many low-resource languages (LRLs) do not have such lexicons, and due to the same reas…