GIFT: Graph-Induced Fine-Tuning for Multi-Party Conversation Understanding.

Jia-Chen Gu Zhenhua Ling Quan Liu Cong Liu Guoping Hu

Published in: ACL (1) (2023)

Keyphrases

multi party
fine tuning
privacy preserving
turn taking
human communication
viable alternative
fine tune
graph representation
fine tuned
graph theory
graph structure
graph mining
description language
bipartite graph
virtual humans
random walk
audio video
multi issue
dynamic programming