Your browser does not support JavaScript!

Home    Search  

Results - Details

Search command : Author="Φλουρής"  And Author="Γεώργιος"

Current Record: 3 of 21

Back to Results Previous page
Next page
Add to Basket
[Add to Basket]
Identifier 000438378
Title Keyword search with multiple interactive perspectives and question answering over RDF datasets
Alternative Title Αναζήτηση μέσω λέξεων-κλειδιών με πολλαπλές διαδραστικές προβολές και απάντηση ερωτήσεων επί συνόλων δεδομένων RDF
Author Νίκας, Χρήστος Β.
Thesis advisor Τζίτζικας, Ιωάννης
Reviewer Πλεξουσάκης, Δημήτρης
Πρατικάκης, Πολύβιος
Φλουρής, Γεώργιος
Abstract Since the task of accessing RDF datasets through structured query languages like SPARQL is rather demanding for ordinary users, there are various approaches that attempt to exploit the simpler and widely used keyword-based search paradigm. However, this task is challenging since there is no clear unit of retrieval and presentation, the user information needs are in most cases not clearly formulated, the underlying RDF datasets are in most cases incomplete, and there is not a single presentation method appropriate for all kinds of information needs. As a means to alleviate these problems, in this thesis we investigate a multi-perspective interaction approach that offers to the user multiple interactive views of the search results, allowing the user to easily switch between these perspectives and thus exploit the added value that each such perspective offers. We present a set of fundamental perspectives, we discuss the benefits from each one, we compare the proposed approach with related existing systems and report the results of a task-based evaluation with users. The key finding of the taskbased evaluation is that users not familiar with RDF (a) managed to complete the information-seeking tasks with performance very close to that of the experienced users, and (b) they rated positively the approach. We also focus on the Question Answering Perspective and to this end we introduce a QA pipeline that involves a general purpose entity search service over RDF, SPARQL, and pre-trained neural networks, including a two-stage method for semantic answer type prediction using BERT and class-specificity rewarding, and finally we report very promising quantitative results over well-known benchmarks.
Language English
Issue date 2021-03-26
Collection   School/Department--School of Sciences and Engineering--Department of Computer Science--Post-graduate theses
  Type of Work--Post-graduate theses
Permanent Link https://elocus.lib.uoc.gr//dlib/1/6/e/metadata-dlib-1615979322-375172-19323.tkl Bookmark and Share
Views 646

Digital Documents
No preview available

Download document
View document
Views : 9