: Published in Information Processing & Management , this paper presents a way to improve how distinct and interpretable topics are within a model.
: This highly regarded paper from arXiv challenges current automated metrics and advocates for human-centered evaluation in neural models. tarea656
: Best for smaller datasets where interpretability is key and computational resources are limited. : Published in Information Processing & Management ,
: A comprehensive review available on Springer that categorizes methods, applications, and future directions for the field. and future directions for the field.