Paper ID | HLT-11.4 | ||
Paper Title | HANDLING CLASS IMBALANCE IN LOW-RESOURCE DIALOGUE SYSTEMS BY COMBINING FEW-SHOT CLASSIFICATION AND INTERPOLATION | ||
Authors | Vishal Sunder, Eric Fosler-Lussier, The Ohio State University, United States | ||
Session | HLT-11: Language Understanding 3: Speech Understanding - General Topics | ||
Location | Gather.Town | ||
Session Time: | Thursday, 10 June, 13:00 - 13:45 | ||
Presentation Time: | Thursday, 10 June, 13:00 - 13:45 | ||
Presentation | Poster | ||
Topic | Human Language Technology: [HLT-DIAL] Discourse and Dialog | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | Utterance classification performance in low-resource dialogue systems is constrained by an inevitably high degree of data imbalance in class labels. We present a new end-to-end pairwise learning framework that is designed specifically to tackle this phenomenon by inducing a few-shot classification capability in the utterance representations and augmenting data through an interpolation of utterance representations. Our approach is a general purpose training methodology, agnostic to the neural architecture used for encoding utterances. We show significant improvements in macro-F1 score over standard cross-entropy training for three different neural architectures, demonstrating improvements on a Virtual Patient dialogue dataset as well as a low-resourced emulation of the Switchboard dialogue act classification dataset. |