Supervised fine-tuning (SFT), supervised instruction tuning (SIT) and in-context learning
(ICL) are three alternative, de facto standard approaches to few-shot learning. ICL has …

Recent advancements in high-quality, large-scale English resources have pushed the
frontier of English Automatic Text Simplification (ATS) research. However, less work has …

Historically, researchers and consumers have noticed a decrease in quality when applying
NLP tools to minority variants of languages (ie Puerto Rican Spanish or Swiss German), but …

Parameter Efficient Tuning has been an prominent approach to adapt the Large Language
Model to downstream tasks. Most previous works considers adding the dense trainable …

Cross-lingual semantic parsing transfers parsing capability from a high-resource language
(eg, English) to low-resource languages with scarce training data. Previous work has …

Language technologies should be judged on their usefulness in real-world use cases. An
often overlooked aspect in natural language processing (NLP) research and evaluation is …

Task-oriented dialogue (ToD) systems help users execute well-defined tasks across a
variety of domains (eg, $\textit {flight booking} $ or $\textit {food ordering} $), with their …

Sinhala is the native language of the Sinhalese people who make up the largest ethnic
group of Sri Lanka. The language belongs to the globe-spanning language tree, Indo …

Achieving robust language technologies that can perform well across the world's many
languages is a central goal of multilingual NLP. In this work, we take stock of and empirically …

Multi-task learning (MTL) benefits the fine-tuning of large language models (LLMs) by
providing a single model with improved performance and generalization ability across tasks …