Multi-Task End-to-End Training Improves Conversational Recommendation

no code implementations • 8 May 2023 • Naveen Ram, Dima Kuzmin, Ellie Ka In Chio, Moustafa Farid Alzantot, Santiago Ontanon, Ambarish Jash, Judith Yue Li

In this paper, we analyze the performance of a multitask end-to-end transformer model on the task of conversational recommendations, which aim to provide recommendations based on a user's explicit preferences expressed in dialogue.

Dialogue Management Management +1

Say What? Collaborative Pop Lyric Generation Using Multitask Transfer Learning

no code implementations • 15 Nov 2021 • Naveen Ram, Tanay Gummadi, Rahul Bhethanabotla, Richard J. Savery, Gil Weinberg

In this paper, we present a collaborative line-level lyric generation system that utilizes transfer-learning via the T5 transformer model, which, till date, has not been used to generate pop lyrics.

Text Generation Transfer Learning