Creating high-quality annotated data for task-oriented dialog (ToD) is known to be
notoriously difficult, and the challenges are amplified when the goal is to create equitable …

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 …

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 …

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 …

Large Language Models (LLMs), such as ChatGPT, are becoming increasingly
sophisticated, demonstrating capabilities that closely resemble those of humans. These AI …

Spoken Language Understanding (SLU) is one of the core components of a task-oriented
dialogue system, which aims to extract the semantic meaning of user queries (eg, intents …

Large multilingual pretrained language models (mPLMs) have become the de facto state of
the art for cross-lingual transfer in NLP. However, their large-scale deployment to many …

Large Language Models (LLMs) have sparked substantial interest and debate concerning
their potential emergence of Theory of Mind (ToM) ability. Theory of mind evaluations …

We present Speech-MASSIVE, a multilingual Spoken Language Understanding (SLU)
dataset comprising the speech counterpart for a portion of the MASSIVE textual corpus …

Generalization and robustness to input variation are core desiderata of machine learning
research. Language varies along several axes, most importantly, language instance (eg …