Recurrent Networks in AQA Answer Selection

D 2018

Recurrent Networks in AQA Answer Selection

SABOL, Radoslav, Marek MEDVEĎ a Aleš HORÁK

Základní údaje

Originální název

Recurrent Networks in AQA Answer Selection

Autoři

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

Vydání

Brno, Proceedings of the Twelfth Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN 2018, od s. 53-62, 10 s. 2018

Nakladatel

Tribun EU

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10200 1.2 Computer and information sciences

Stát vydavatele

Česká republika

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

tištěná verze "print"

Odkazy

URL

Kód RIV

RIV/00216224:14330/18:00101541

Organizační jednotka

Fakulta informatiky

ISBN

978-80-263-1517-9

ISSN

UT WoS

000612420300007

Klíčová slova anglicky

question answering; answer selection; QA dataset; SQAD; AQA

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 20. 9. 2022 11:11, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

Unlimited, or open domain, question answering system AQA is being developed and tested with the Simple Question Answering Data-base (SQAD) for the Czech language. AQA is optimized for work with morphologically rich languages and makes use of syntactic cues provided by the morphosyntactic analysis. In this paper, we introduce a new answer selection module being developed for the AQA system. The module is based on recurrent neural networks processing the question and answer sentences to derive the most probable answer sentence. We present the details of the module architecture and offer a detailed evaluation of various hyperparameter setups. The module is trained and tested with 8,500 question-answer pairs using the SQAD v2.1 benchmark dataset.

Návaznosti

GA18-23891S, projekt VaV

Název: Hyperintensionální usuzování nad texty přirozeného jazyka

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

Citovat

SABOL, Radoslav, Marek MEDVEĎ a Aleš HORÁK. Recurrent Networks in AQA Answer Selection. In Aleš Horák, Pavel Rychlý and Adam Rambousek. Proceedings of the Twelfth Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN 2018. Brno: Tribun EU, 2018, s. 53-62. ISBN 978-80-263-1517-9.

@inproceedings{1484740,
   author = {Sabol, Radoslav and Medveď, Marek and Horák, Aleš},
   address = {Brno},
   booktitle = {Proceedings of the Twelfth Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN 2018},
   editor = {Aleš Horák, Pavel Rychlý and Adam Rambousek},
   keywords = {question answering; answer selection; QA dataset; SQAD; AQA},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Brno},
   isbn = {978-80-263-1517-9},
   pages = {53-62},
   publisher = {Tribun EU},
   title = {Recurrent Networks in AQA Answer Selection},
   url = {https://nlp.fi.muni.cz/raslan/2018/paper12-Sabol_Medved_Horak.pdf},
   year = {2018}
}

TY  - JOUR
ID  - 1484740
AU  - Sabol, Radoslav - Medveď, Marek - Horák, Aleš
PY  - 2018
TI  - Recurrent Networks in AQA Answer Selection
PB  - Tribun EU
CY  - Brno
SN  - 9788026315179
KW  - question answering
KW  - answer selection
KW  - QA dataset
KW  - SQAD
KW  - AQA
UR  - https://nlp.fi.muni.cz/raslan/2018/paper12-Sabol_Medved_Horak.pdf
N2  - Unlimited, or open domain, question answering system AQA is being developed and tested with the Simple Question Answering Data-base (SQAD) for the Czech language. AQA is optimized for work with morphologically rich languages and makes use of syntactic cues provided by the morphosyntactic analysis. In this paper, we introduce a new answer selection module being developed for the AQA system. The module is based on recurrent neural networks processing the question and answer sentences to derive the most probable answer sentence. We present the details of the module architecture and offer a detailed evaluation of various hyperparameter setups. The module is trained and tested with 8,500 question-answer pairs using the SQAD v2.1 benchmark dataset.
ER  -

SABOL, Radoslav, Marek MEDVEĎ a Aleš HORÁK. Recurrent Networks in AQA Answer Selection. In Aleš Horák, Pavel Rychlý and Adam Rambousek. \textit{Proceedings of the Twelfth Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN 2018}. Brno: Tribun EU, 2018, s.~53-62. ISBN~978-80-263-1517-9.

Podrobný výpis o publikaci