Please use this identifier to cite or link to this item: http://hdl.handle.net/10362/142633
Title: INCM & Nova Sbe PBL project - retirement law query system: using top ranking to improve user experience in a semantic search system
Author: Cardoso, Diogo Nasser
Advisor: Xufre, Patrícia
Magalhães, João
Keywords: Machine learning
Business analytics
Natural language processing
Chatbot
Nlp
Incm
Bert
Haystack
Law query system
Semantic search
Feedback
Top ranking
User experience
Retirement law
Big data analysis
Defense Date: 20-Jan-2022
Abstract: This study measures how Portuguese BERT performs as a semantic search system for the Portuguese Retirement Law by comparing the proposed solution answers with a test set. The study also envision edhowa feedback method (Top-Ranking)would be implemented in the developed system. This solution aimed to reorder the questions returned by the mode l based on semantic similarity. The semantic search solution showed positive results, but the Top-Ranking method failed to be implemented as the metric for semantic similarity delivered inconsistent results, thus failing to provide a solid structure for such system. The client showed very positive feedback regarding the developed tool, especially when comparing it with the current implemented solution. This project showed that Portuguese BERT is a tool with a lot of potential for semantic search on various other domains.
URI: http://hdl.handle.net/10362/142633
Designation: A Work Project, presented as part of the requirements for the Award of a Masters Degree in Management from the NOVA – School of Business and Economics
Appears in Collections:NSBE: Nova SBE - MA Dissertations

Files in This Item:
File Description SizeFormat 
021-22_fall_50746_diogo-cardoso.pdf2,26 MBAdobe PDFView/Open


FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpace
Formato BibTex MendeleyEndnote 

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.