[ Skip to the content ]

Institute of Formal and Applied Linguistics

at Faculty of Mathematics and Physics, Charles University, Prague, Czech Republic


[ Back to the navigation ]

Publication


Year 2016
Type in proceedings
Status published
Language English
Author(s) Víta, Martin Kríž, Vincent
Title Word2vec Based System for Recognizing Partial Textual Entailment
Czech title Word2vec systém pro rozpoznávání Partial Textual Entailment
Proceedings 2016: New York City, NY, USA: FedCSIS: Proceedings of the 2016 Federated Conference on Computer Science and Information Systems
Pages range 513-516
How published print
Supported by 2016 SVV 260 333 (Teoretické základy informatiky a výpočetní lingvistiky)
Czech abstract 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.
English abstract 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.
Specialization linguistics ("jazykověda")
Confidentiality default – not confidential
Open access no
DOI 10.15439/2016F419
Editor(s)* Maria Ganzha; Leszek Bednarczuk; Marcin Paprzycki
ISBN* 978-83-60810-90-3
ISSN* 2300-5963
Address* New York City, NY, USA
Month* September
Publisher* Institute of Electrical and Electronics Engineers
Institution* Polskie Towarzystwo Informatyczne
Organization* Institute of Electrical and Electronics Engineers
Creator: Common Account
Created: 10/7/16 10:39 AM
Modifier: Almighty Admin
Modified: 2/25/17 10:07 PM
***

Content, Design & Functionality: ÚFAL, 2006–2016. Page generated: Sat Sep 23 22:05:18 CEST 2017

[ Back to the navigation ] [ Back to the content ]

100% OpenAIRE compliant