Employing Sentence Context in Czech Answer Selection

D 2020

Employing Sentence Context in Czech Answer Selection

MEDVEĎ, Marek, Aleš HORÁK a Radoslav SABOL

Základní údaje

Originální název

Employing Sentence Context in Czech Answer Selection

Autoři

MEDVEĎ, Marek (703 Slovensko, garant, domácí), Aleš HORÁK (203 Česká republika, domácí) a Radoslav SABOL (703 Slovensko, domácí)

Vydání

Switzerland, Text, Speech, and Dialogue. TSD 2020, od s. 112-121, 10 s. 2020

Nakladatel

Springer, Cham

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Švýcarsko

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

tištěná verze "print"

Impakt faktor

Impact factor: 0.402 v roce 2005

Kód RIV

RIV/00216224:14330/20:00114572

Organizační jednotka

Fakulta informatiky

ISBN

978-3-030-58322-4

ISSN

DOI

http://dx.doi.org/10.1007/978-3-030-58323-1_12

UT WoS

000611543200012

Klíčová slova anglicky

question answering;answer selection;Czech;answer context;morphologically rich languages

Štítky

firank_B

Změněno: 29. 4. 2021 08:12, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

Question answering (QA) of non-mainstream languages requires specific adaptations of the current methods tested primarily with very large English resources. In this paper, we present the results of improving the QA answer selection task by extending the input candidate sentence with selected information from preceding sentence context. The described model represents the best published answer selection model for the Czech language as an example of a morphologically rich language. The text contains thorough evaluation of the new method including model hyperparameter combinations and detailed error discussion. The winning models have improved the previous best results by 4% reaching the mean average precision of 82.91%.

Návaznosti

GA18-23891S, projekt VaV

Název: Hyperintensionální usuzování nad texty přirozeného jazyka

Investor: Grantová agentura ČR, Hyperintensionální usuzování nad texty přirozeného jazyka

Citovat

MEDVEĎ, Marek, Aleš HORÁK a Radoslav SABOL. Employing Sentence Context in Czech Answer Selection. In Sojka P., Kopeček I., Pala K., Horák A. Text, Speech, and Dialogue. TSD 2020. Switzerland: Springer, Cham, 2020, s. 112-121. ISBN 978-3-030-58322-4. Dostupné z: https://dx.doi.org/10.1007/978-3-030-58323-1_12.

@inproceedings{1709742,
   author = {Medveď, Marek and Horák, Aleš and Sabol, Radoslav},
   address = {Switzerland},
   booktitle = {Text, Speech, and Dialogue. TSD 2020},
   doi = {http://dx.doi.org/10.1007/978-3-030-58323-1_12},
   editor = {Sojka P., Kopeček I., Pala K., Horák A.},
   keywords = {question answering;answer selection;Czech;answer context;morphologically rich languages},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Switzerland},
   isbn = {978-3-030-58322-4},
   pages = {112-121},
   publisher = {Springer, Cham},
   title = {Employing Sentence Context in Czech Answer Selection},
   year = {2020}
}

TY  - JOUR
ID  - 1709742
AU  - Medveď, Marek - Horák, Aleš - Sabol, Radoslav
PY  - 2020
TI  - Employing Sentence Context in Czech Answer Selection
PB  - Springer, Cham
CY  - Switzerland
SN  - 9783030583224
KW  - question answering;answer selection;Czech;answer context;morphologically rich languages
N2  - Question answering (QA) of non-mainstream languages requires specific adaptations of the current methods tested primarily with very large English resources. In this paper, we present the results of improving the QA answer selection task by extending the input candidate sentence with selected information from preceding sentence context. The described model represents the best published answer selection model for the Czech language as an example of a morphologically rich language. The text contains thorough evaluation of the new method including model hyperparameter combinations and detailed error discussion. The winning models have improved the previous best results by 4% reaching the mean average precision of 82.91%.
ER  -

MEDVEĎ, Marek, Aleš HORÁK a Radoslav SABOL. Employing Sentence Context in Czech Answer Selection. In Sojka P., Kopeček I., Pala K., Horák A. \textit{Text, Speech, and Dialogue. TSD 2020}. Switzerland: Springer, Cham, 2020, s.~112-121. ISBN~978-3-030-58322-4. Dostupné z: https://dx.doi.org/10.1007/978-3-030-58323-1\_{}12.

Podrobný výpis o publikaci