March 27, 2024, 4:48 a.m. | Yuxiang Nie, Heyan Huang, Xian-Ling Mao, Lizi Liao

cs.CL updates on arXiv.org arxiv.org

arXiv:2403.17636v1 Announce Type: new
Abstract: Mixed initiative serves as one of the key factors in controlling conversation directions. For a speaker, responding passively or leading proactively would result in rather different responses. However, most dialogue systems focus on training a holistic response generation model without any distinction among different initiatives. It leads to the cross-contamination problem, where the model confuses different initiatives and generates inappropriate responses. Moreover, obtaining plenty of human annotations for initiative labels can be expensive. To address …

abstract arxiv conversation cs.cl dialogue dynamic focus however key leads mixed responses speaker systems the key training type

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne

Senior Machine Learning Engineer (MLOps)

@ Promaton | Remote, Europe

Principal Data Engineering Manager

@ Microsoft | Redmond, Washington, United States

Machine Learning Engineer

@ Apple | San Diego, California, United States