Výsledky vyhledávání - "Perevalov, Aleksandr"

Report

QALD-9-plus: A Multilingual Dataset for Question Answering over DBpedia and Wikidata Translated by Native Speakers

Autor: Perevalov, Aleksandr, Diefenbach, Dennis, Usbeck, Ricardo, Both, Andreas

The ability to have the same experience for different user groups (i.e., accessibility) is one of the most important characteristics of Web-based systems. The same is true for Knowledge Graph Question Answering (KGQA) systems that provide the access

Externí odkaz: http://arxiv.org/abs/2202.00120

Zobrazit plný text záznamu

Report

Knowledge Graph Question Answering Leaderboard: A Community Resource to Prevent a Replication Crisis

Autor: Perevalov, Aleksandr, Yan, Xi, Kovriguina, Liubov, Jiang, Longquan, Both, Andreas, Usbeck, Ricardo

Data-driven systems need to be evaluated to establish trust in the scientific approach and its applicability. In particular, this is true for Knowledge Graph (KG) Question Answering (QA), where complex data structures are made accessible via natural-

Externí odkaz: http://arxiv.org/abs/2201.08174

Zobrazit plný text záznamu

Report

Improving the Question Answering Quality using Answer Candidate Filtering based on Natural-Language Features

Autor: Gashkov, Aleksandr, Perevalov, Aleksandr, Eltsova, Maria, Both, Andreas

Software with natural-language user interfaces has an ever-increasing importance. However, the quality of the included Question Answering (QA) functionality is still not sufficient regarding the number of questions that are answered correctly. In our

Externí odkaz: http://arxiv.org/abs/2112.05452

Zobrazit plný text záznamu

Report

Question Embeddings Based on Shannon Entropy: Solving intent classification task in goal-oriented dialogue system

Autor: Perevalov, Aleksandr, Kurushin, Daniil, Faizrakhmanov, Rustam, Khabibrakhmanova, Farida

Publikováno v: 2019/03/06, Volume 7, Issue 1, Koethen Germany, ISBN: 978-3-96057-086-8 (Online)

Question-answering systems and voice assistants are becoming major part of client service departments of many organizations, helping them to reduce the labor costs of staff. In many such systems, there is always natural language understanding module

Externí odkaz: http://arxiv.org/abs/1904.00785

Zobrazit plný text záznamu