Adithya Sagar

CoDi: Conversational Distillation for Grounded Question Answering

2024 · arXiv (Cornell University)

Distilling conversational skills into Small Language Models (SLMs) with approximately 1 billion parameters presents significant challenges. Firstly, SLMs have limited capacity in their model parameters to learn extensive knowledge compared to larger models. Secondly, high-quality …

PRoDeliberation: Parallel Robust Deliberation for End-to-End Spoken Language Understanding

2024

Spoken Language Understanding (SLU) is a critical component of voice assistants; it consists of converting speech to semantic parses for task execution.Previous works have explored end-to-end models to improve the quality and robustness of SLU …