2023/11/15 by N. V. Narendra Kumar, Ondřej Dušek, Kumar, Nalin +1 · 1 citation
Computer Science · #AI in Service Interactions #Computation and Language (cs.CL) #FOS: Computer and information sciences #Speech and dialogue systems #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2311.09390
openalex publication_date 2023/11/15 · openalex created_date 2023/11/18 · openalex updated_date 2026/07/28
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 task-oriented 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. We demonstrate that all three approaches produce significantly better entrainment than the base, non-entrainment-optimized model, as confirmed by both automated and manual evaluation metrics.