Iranian Healthcare magazines have been published in Iran to inform the public of the COVID-19 crisis . However, finding answers in this volume of information is an extremely difficult task . With the surge of pretrained language models, a new pathway has been opened to incorporate Persian text contextual information . We fine-tune our models using Semantic TextualSimilarity and evaluate them with standard task metrics . Our final search engine consists of a ranker and a re-ranker, whichadapts itself to the query. Our final methodoutperforms the rest of the rest by a considerable margin. It is a search engine to sift through these documents and rank them, given a user’s query.

Author(s) : Reza Khanmohammadi, Mitra Sadat Mirshafiee, Mehdi Allahyari

Links : PDF - Abstract

Code :
Coursera

Keywords : engine - search - query - rest - task -

Leave a Reply

Your email address will not be published. Required fields are marked *