Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F16%3A10335456" target="_blank" >RIV/00216208:11320/16:10335456 - isvavai.cz</a>
Result on the web
<a href="http://www.aclweb.org/anthology/P/P16/P16-2008.pdf" target="_blank" >http://www.aclweb.org/anthology/P/P16/P16-2008.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings
Original language description
We present a natural language generator based on the sequence-to-sequence approach that can be trained to produce natural language strings as well as deep syntax dependency trees from input dialogue acts, and we use it to directly compare two-step generation with separate sentence planning and surface realization stages to a joint, one-step approach. We were able to train both setups successfully using very little training data. The joint setup offers better performance, surpassing state-of-the-art with regards to n-gram-based scores while providing more relevant outputs.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2016
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 the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
ISBN
978-1-945626-01-2
ISSN
—
e-ISSN
—
Number of pages
7
Pages from-to
45-51
Publisher name
Association for Computational Linguistics
Place of publication
Stroudsburg, PA, USA
Event location
Berlin, Germany
Event date
Aug 7, 2016
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—