Enhancing local citation recommendation with recurrent highway networks and SciBERT-based embedding

Dinh, Thi N.; Pham, Phu; Nguyen, Giang L.; Vo, Bay

doi:10.1016/j.eswa.2023.122911

Cited by 2 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The very first layer, as shown in Figure 2, is an embedding layer [60][61][62], which is a layer in neural networks that transforms the input data into a form that is easy to manage and can be efficiently handled in the network. In text processing, for a language model, it transforms words into vectors that represent those words in a field.…”

Section: Layersmentioning

confidence: 99%

Advancing Medical Assistance: Developing an Effective Hungarian-Language Medical Chatbot with Artificial Intelligence

Simon,

Hartveg,

Dénes-Fazakas

et al. 2024

Information

View full text Add to dashboard Cite

In recent times, the prevalence of chatbot technology has notably increased, particularly in the realm of medical assistants. However, there is a noticeable absence of medical chatbots that cater to the Hungarian language. Consequently, Hungarian-speaking people currently lack access to an automated system capable of providing assistance with their health-related inquiries or issues. Our research aims to establish a competent medical chatbot assistant that is accessible through both a website and a mobile app. It is crucial to highlight that the project’s objective extends beyond mere linguistic localization; our goal is to develop an official and effectively functioning Hungarian chatbot. The assistant’s task is to answer medical questions, provide health advice, and inform users about health problems and treatments. The chatbot should be able to recognize and interpret user-provided text input and offer accurate and relevant responses using specific algorithms. In our work, we put a lot of emphasis on having steady input so that it can detect all the diseases that the patient is dealing with. Our database consisted of sentences and phrases that a user would type into a chatbot. We assigned health problems to these and then assigned the categories to the corresponding cure. Within the research, we developed a website and mobile app, so that users can easily use the assistant. The app plays a particularly important role for users because it allows them to use the assistant anytime and anywhere, taking advantage of the portability of mobile devices. At the current stage of our research, the precision and validation accuracy of the system is greater than 90%, according to the selected test methods.

show abstract

Section: Layersmentioning

confidence: 99%