Další formáty:
BibTeX
LaTeX
RIS
@inproceedings{1377657,
author = {Víta, Martin and Kríž, Vincent},
address = {NEW YORK},
booktitle = {PROCEEDINGS OF THE 2016 FEDERATED CONFERENCE ON COMPUTER SCIENCE AND INFORMATION SYSTEMS (FEDCSIS)},
doi = {http://dx.doi.org/10.15439/2016F419},
editor = {Ganzha, M Maciaszek, L Paprzycki, M},
keywords = {textual entailment; word2vec model; faceted entailment},
howpublished = {elektronická verze "online"},
language = {eng},
location = {NEW YORK},
isbn = {978-83-60810-90-3},
pages = {513-516},
publisher = {IEEE},
title = {Word2vec Based System for Recognizing Partial Textual Entailment},
year = {2016}
}
TY - JOUR
ID - 1377657
AU - Víta, Martin - Kríž, Vincent
PY - 2016
TI - Word2vec Based System for Recognizing Partial Textual Entailment
PB - IEEE
CY - NEW YORK
SN - 9788360810903
KW - textual entailment
KW - word2vec model
KW - faceted entailment
N2 - 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 IT 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 NIT tools and other linguistic resources, therefore it can he easily implemented in different language environments where word2vec models are available.
ER -
VÍTA, Martin a Vincent KRÍŽ. Word2vec Based System for Recognizing Partial Textual Entailment. Online. In Ganzha, M Maciaszek, L Paprzycki, M. \textit{PROCEEDINGS OF THE 2016 FEDERATED CONFERENCE ON COMPUTER SCIENCE AND INFORMATION SYSTEMS (FEDCSIS)}. NEW YORK: IEEE, 2016, s.~513-516. ISBN~978-83-60810-90-3. Dostupné z: https://dx.doi.org/10.15439/2016F419.
|
