公开(公告)号：US20220358384A1

公开(公告)日：2022-11-10

申请号：US17736683

申请日：2022-05-04

申请人： Arizona Board of Regents on Behalf of the University of Arizona

发明人： Mithun Paul ,  Mihai Surdeanu ,  Sandeep Suntwal ,  Rebecca Sharp

IPC分类号： G06N5/04 ,  G06N5/02 ,  G06N3/08 ,  G06N3/04

摘要： A domain fact verification system is described having a computer programmed with a model trained using a process of data distillation and model distillation to improve model learning of the underlying semantics of a dataset rather than relying on statistical and lexical nuances in a domain-specific dataset. The computer thus programmed can accurately perform fact verification across multiple domains without the labor-intensive process of encoding a dataset of human-annotated, domain-specific information for each domain. Moreover, by combining data distillation with model distillation techniques, which may be seen as an inverse of well-established ensemble strategies (which train individual models separately and applies them jointly) the present domain transferable fact verification system scales better at inference time due to its reliance on a single trained model.