Politician -- An Imitation Game
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F18%3A10390113" target="_blank" >RIV/00216208:11320/18:10390113 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Politician -- An Imitation Game
Original language description
We present the question-answering system Politician, which is a chatbot designed to imitate a fictional politician. The chatbot accepts questions on political issues and answers them accordingly. The questions are analyzed using natural language processing techniques, mainly using a custom scenario built on Treex, and no complex knowledge base is involved. There are two working versions so far, in Czech and in English. Once morphological and syntactic annotations are available for the question, an appropriate answer template is selected from the manually created set of answer templates based on the nouns, verbs and named entities present in the question. After that, the answer template is transformed into a grammatically correct reply. We also briefly investigated the differences between the two languages and potential generalization of the approach to other topics. Apparently, morphological and syntactic information provides enough data for a very basic understanding of questions on a specific topic.
Czech name
—
Czech description
—
Classification
Type
C - Chapter in a specialist book
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
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2018
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Book/collection name
Internet Science
ISBN
978-3-319-77546-3
Number of pages of the result
12
Pages from-to
201-212
Number of pages of the book
258
Publisher name
Springer International Publishing
Place of publication
Cham, Switzerland
UT code for WoS chapter
—