LEEETs-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems

Anonymous

TL;DR: Increasing linguistic entrainment for task-oriented end-to-end dialogue systems

Abstract: Linguistic entrainment, or alignment, represents a phenomenon where linguistic patterns employed by conversational participants converge to one another. While entrainment has been shown to produce a more natural user experience, most dialogue systems do not have any provisions for it. In this work, we introduce methods for achieving dialogue entrainment in a GPT-2-based end-to-end dialogue system through the utilization of shared vocabulary. We experiment with training instance weighting, entrainment-specific loss, and additional conditioning to generate responses that align with the user. By comparing different entrainment techniques on the MultiWOZ dataset, we demonstrate that all three approaches produce significantly better entrainment than the baseline, as confirmed by both automated and manual evaluation metrics.

Paper Type: short

Research Area: Dialogue and Interactive Systems

Contribution Types: Model analysis & interpretability, NLP engineering experiment

Languages Studied: English