An Open-Domain QA System for e-Governance

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. © 2022, Institute for Bulgarian Language. All rights reserved.

The role of automatic speech recognition systems in developing medical applications

Technological progress in recent years has impacted the medical system, leading to the emergence of new technologies specific to the medical field. Important resources have been directed to transform the medical system. The most recent include digital scribes, voice biomarkers and medical IoT. In some segments, the performance of the systems was improved by the use of technologies such as automatic speech recognition and natural language processing. While medical notes were shorthanded in the 20th century, today the healthcare system has begun to adopt ASR-based technologies to transcribe conversations between doctors and patients. An ASR technology that can accelerate transcription of the clinical conversation has an immediate positive impact on the medical act. ASR-centered technologies are now part of the offering of big software development companies, such as Google, Amazon, IBM, etc. These companies and others, including many startups, have entered the race to offer different types of Machine Learning technologies that support medical services to facilitate the work of clinical workers: electronic health records and automated digital scribes use ASR and NLP to automatically transcribe patient-clinician conversations and medical notes. Voice biomarkers are being used to develop automated solutions that can identify and monitor health conditions such as Parkinson's Disease or screen potential COVID- 19 infections. The IoT computing paradigm is being used within a medical context in what is known as the Internet of Medical Things to deliver lowlatency Edge computing that enables a new generation of medical apps. © 2022 Nova Science Publishers, Inc..