Towards General Document Understanding through Question Answering
| Authors | |
|---|---|
| Year of publication | 2022 |
| Type | Article in Proceedings |
| Conference | Recent Advances in Slavonic Natural Language Processing (RASLAN 2022) |
| MU Faculty or unit | |
| Citation | |
| Web | fulltext PDF |
| Keywords | Question Answering; Visual Question Answering; Document Visual Question Answering |
| Description | Document Visual Question Answering is a relatively new extension of Visual Question Answering. The aim is to understand the documents and to be able to obtain information that corresponds to the question that was asked. This proposition aims to approach the problem of the lack of datasets and a model for Slavic languages. Therefore we would like to create a model and dataset for Document VQA suitable for the non-English language. This paper overviews the field of Question Answering and also describes the first Czech Document VQA dataset and model. |
| Related projects: |