Constrained Deep Answer Sentence Selection
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F17%3A10372135" target="_blank" >RIV/00216208:11320/17:10372135 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1007/978-3-319-64206-2_7" target="_blank" >https://doi.org/10.1007/978-3-319-64206-2_7</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-319-64206-2_7" target="_blank" >10.1007/978-3-319-64206-2_7</a>
Alternative languages
Result language
angličtina
Original language name
Constrained Deep Answer Sentence Selection
Original language description
We propose Constrained Deep Neural Network (CDNN) a deep neural model for answer sentence selection in the context of Question Answering (QA) systems. To produce the best predictions, CDNN combines neural reasoning with a kind of symbolic constraint. It integrates pattern matching technique into sentence vector learning. When trained using enough samples, CDNN outperforms the other best models for sentence selection. We show how the use of other sources of training can enhance the performance of CDNN. In a well-studied dataset for answer sentence selection, our model improves the state-of-the-art significantly
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
20th International Conference, TSD 2017 Prague, Czech Republic, August 27–31, 2017 Proceedings
ISBN
978-3-319-64205-5
ISSN
0302-9743
e-ISSN
neuvedeno
Number of pages
9
Pages from-to
57-65
Publisher name
Springer International Publishing
Place of publication
Cham / Heidelberg / New York
Event location
Praha, Czechia
Event date
Aug 27, 2016
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—