Hybrid Deep Open-Domain Question Answering
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F17%3A10372134" target="_blank" >RIV/00216208:11320/17:10372134 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Hybrid Deep Open-Domain Question Answering
Original language description
In this short paper, we report a progressing work on a hybrid deep neural system for answering open-domain factoid and non-factoid questions. This system supplements knowledge graph based Question Answering with free-texts searching techniques to address the sparsity issues in knowledge graphs. We justify the efficiency of the proposed system based on the results of a pilot experiment. We also describe the settings of an on-going project in the context of this system.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2017
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of 8th Language and Technology Conference
ISBN
978-83-64864-94-0
ISSN
—
e-ISSN
neuvedeno
Number of pages
5
Pages from-to
163-167
Publisher name
Fundacja Uniwersytetu im. Adama Mickiewicza w Poznaniu
Place of publication
Poznań, Poland
Event location
Poznań, Poland
Event date
Nov 17, 2017
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—