Word2vec Based System for Recognizing Partial Textual Entailment

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F16%3A10335541" target="_blank" >RIV/00216208:11320/16:10335541 - isvavai.cz</a>
Alternative codes found
RIV/00216224:14330/16:00094081
Result on the web
<a href="http://dx.doi.org/10.15439/2016F419" target="_blank" >http://dx.doi.org/10.15439/2016F419</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.15439/2016F419" target="_blank" >10.15439/2016F419</a>

Result language
angličtina
Original language name
Word2vec Based System for Recognizing Partial Textual Entailment
Original language description
Recognizing textual entailment is typically considered as a binary decision task - whether a text T entails a hypothesis H. Thus, in case of a negative answer, it is not possible to express that H is "almost entailed" by T. Partial textual entailment provides one possible approach to this issue. This paper presents an attempt to use word2vec model for recognizing partial (faceted) textual entailment. The proposed approach does not rely on language dependent NLP tools and other linguistic resources, therefore it can be easily implemented in different language environments where word2vec models are available.
Czech name
—
Czech description
—

Publication year
2016
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the 2016 Federated Conference on Computer Science and Information Systems
ISBN
978-83-60810-90-3
ISSN
2300-5963
e-ISSN
—
Number of pages
4
Pages from-to
513-516
Publisher name
Institute of Electrical and Electronics Engineers
Place of publication
New York City, NY, USA
Event location
Gdańsk, Poland
Event date
Sep 11, 2016
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)