Christopher DiPersio
YOU?
Author Swipe
View article: CALICO: Conversational Agent Localization via Synthetic Data Generation
CALICO: Conversational Agent Localization via Synthetic Data Generation Open
We present CALICO, a method to fine-tune Large Language Models (LLMs) to localize conversational agent training data from one language to another. For slots (named entities), CALICO supports three operations: verbatim copy, literal transla…
View article: Cross-lingual transfer for low-resource Arabic language understanding
Cross-lingual transfer for low-resource Arabic language understanding Open
This paper explores cross-lingual transfer learning in natural language understanding (NLU), with the focus on bootstrapping Arabic from high-resource English and French languages for domain classification, intent classification, and named…
View article: Using Alternate Representations of Text for Natural Language Understanding
Using Alternate Representations of Text for Natural Language Understanding Open
One of the core components of voice assistants is the Natural Language Understanding (NLU) model. Its ability to accurately classify the user’s request (or “intent”) and recognize named entities in an utterance is pivotal to the success of…