Sydney Defilippo

Research Assistant @Carnegie Mellon University - School Of Computer Science - Language Technologies Institute

Leading research to enhance automatic speech recognition by integrating complex morphological rules into language models, aiming to improve accuracy for low resourced languages. Executing in-depth linguistic fieldwork to construct a full morphological analysis of an endangered Indigenous language, crucial for advancing natural language processing capabilities. Training a neural model to tokenize a corpus according to linguistic segmentation with the goals of speeding up manual segmentation and improving language model perplexity over traditional tokenizers.