Dp 627 en

From DCEwiki
Jump to navigation Jump to search

Unstructured text comprehension and question answering[edit]

Author: Konrád Jakub

Diplomové práce 2018

Stáhnout práci v PDF

This thesis deals with comprehension of unstructured text and question answering. Specifically we focus the benefits of transfer learning. We show several experiments where we employ transfer learning to adjust model created on general large QA dataset (SQuAD) with data from smaller topic specific datasets. We explore influence of transfer learning on datasets focusing on specific topic not included in the main domain.