177 citations
- National University of SingaporeSG7 papers
- The University of MelbourneAU7 papers
- University of ColomboLK6 papers
- École Polytechnique Fédérale de LausanneCH4 papers
- UNSW SydneyAU4 papers
- Boise State UniversityUS3 papers
- Carnegie Mellon UniversityUS3 papers
- Idiap Research InstituteCH3 papers
- Stanford UniversityUS3 papers
- University of RuhunaLK3 papers
- University of Southern QueenslandAU3 papers
- WSO2 (Sri Lanka)LK3 papers
37 papers · 1 filter
GeeSanBhava: Sentiment Tagged Sinhala Music Video Comment Data Set
Yomal De Mel, Nisansa de Silva
This study introduce GeeSanBhava, a high-quality data set of Sinhala song comments extracted from YouTube manually tagged using Russells Valence-Arousal model by three independent…
How Good is BLI as an Alignment Measure: A Study in Word Embedding Paradigm
Kasun Wickramasinghe, Nisansa de Silva
Sans a dwindling number of monolingual embedding studies originating predominantly from the low-resource domains, it is evident that multilingual embedding has become the de facto…
DESS: DeBERTa Enhanced Syntactic-Semantic Aspect Sentiment Triplet Extraction
Vishal Thenuwara, Nisansa de Silva
Fine-grained sentiment analysis faces ongoing challenges in Aspect Sentiment Triple Extraction (ASTE), particularly in accurately capturing the relationships between aspects, opini…
Comparing the Performance of LLMs in RAG-based Question-Answering: A Case Study in Computer Science Literature
Ranul Dayarathne, Uvini Ranaweera, Upeksha Ganegoda
Retrieval Augmented Generation (RAG) is emerging as a powerful technique to enhance the capabilities of Generative AI models by reducing hallucination. Thus, the increasing promine…
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…