Improving RNN-based Answer Selection for Morphologically Rich Languages

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F20%3A00114091" target="_blank" >RIV/00216224:14330/20:00114091 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.5220/0008979206440651" target="_blank" >http://dx.doi.org/10.5220/0008979206440651</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.5220/0008979206440651" target="_blank" >10.5220/0008979206440651</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Improving RNN-based Answer Selection for Morphologically Rich Languages

Popis výsledku v původním jazyce

Question answering systems have improved greatly during the last five years by employing architectures of deep neural networks such as attentive recurrent networks or transformer-based networks with pretrained con- textual information. In this paper, we present the results and detailed analysis of experiments with the largest question answering benchmark dataset for the Czech language. The best results evaluated in the text reach the accuracy of 72 %, which is a 4 % improvement to the previous best result. We also introduce the newest version of the Czech Question Answering benchmark dataset SQAD 3.0, which was substantially extended to more than 13,000 question-answer pairs, and we report the first answer selection results on this dataset which indicate that the size of the training data is important for the task.

Název v anglickém jazyce

Improving RNN-based Answer Selection for Morphologically Rich Languages

Popis výsledku anglicky

Question answering systems have improved greatly during the last five years by employing architectures of deep neural networks such as attentive recurrent networks or transformer-based networks with pretrained con- textual information. In this paper, we present the results and detailed analysis of experiments with the largest question answering benchmark dataset for the Czech language. The best results evaluated in the text reach the accuracy of 72 %, which is a 4 % improvement to the previous best result. We also introduce the newest version of the Czech Question Answering benchmark dataset SQAD 3.0, which was substantially extended to more than 13,000 question-answer pairs, and we report the first answer selection results on this dataset which indicate that the size of the training data is important for the task.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10200 - Computer and information sciences

Projekt

<a href="/cs/project/GA18-23891S" target="_blank" >GA18-23891S: Hyperintensionální usuzování nad texty přirozeného jazyka</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 12th International Conference on Agents and Artificial Intelligence

ISBN

9789897583957

ISSN

2184-433X

e-ISSN

—

Počet stran výsledku

8

Strana od-do

644-651

Název nakladatele

SCITEPRESS

Místo vydání

Portugal

Místo konání akce

Portugal

Datum konání akce

1. 1. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000570769000069