EMNLP 2018.

Abstract

Neural networks models have gained unprecedented popularity in natural language processing due to their state-of-the-art performance and the flexible end-to-end training scheme. Despite their advantages, the lack of interpretability hinders the deployment and refinement of the models. In this work, we present a flexible visualization library for creating customized visual analytic environments, in which the user can investigate and interrogate the relationships among the input, the model internals (i.e., attention), and the output predictions, which in turn shed light on the model decision-making process.

Links

Bib Entry

 
  @InProceedings{D18-2007,
  author = 	"Liu, Shusen
    	and Li, Tao
    	and Li, Zhimin
    	and Srikumar, Vivek
    	and Pascucci, Valerio
    	and Bremer, Peer-Timo",
  title = 	"Visual Interrogation of Attention-Based Models for Natural Language Inference and Machine Comprehension",
  booktitle = 	"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
  year = 	"2018",
  publisher = 	"Association for Computational Linguistics",
  pages = 	"36--41",
  location = 	"Brussels, Belgium",
  url = 	"http://aclweb.org/anthology/D18-2007"
}