An Open-Domain QA System for e-Governance
This work provides a domain-specific tool for e-governance and public information access during the pandemic, but it is incremental as it applies existing methods to a new language and dataset.
The paper developed an open-domain question answering system for Romanian to address COVID-19 related queries, achieving performance through a fine-tuned BERT model on a manually created dataset.
The paper presents an open-domain Question Answering system for Romanian, answering COVID-19 related questions. The QA system pipeline involves automatic question processing, automatic query generation, web searching for the top 10 most relevant documents and answer extraction using a fine-tuned BERT model for Extractive QA, trained on a COVID-19 data set that we have manually created. The paper will present the QA system and its integration with the Romanian language technologies portal RELATE, the COVID-19 data set and different evaluations of the QA performance.