Results - Details
Search command : Author="Φλουρής"
And Author="Γεώργιος"
Current Record: 4 of 22
|
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
|
Views |
719 |