Обогащение контекста вопросов знаниями из ConceptNet для улучшения точности ответов

?

Обогащение контекста вопросов знаниями из ConceptNet для улучшения точности ответов

Modern question answering models can achieve near-human accuracy of answers for factual questions about a given piece of text in English. In the meantime, such models fail to achieve the same performance on datasets of question, which require some background information, not presented in the question context. This paper describes experimental evaluation of simple question context enrichment method based on collecting ConceptNet relations and proposes further direction of work in creating a question answering dataset for Russian language.

Language: Russian

Text on another site

Publication based on the results of:

Intelligent Data Analysis in Interactive Systems for Transdisciplinary Applications (2020)

In book

Компьютерная лингвистика и интеллектуальные технологии: По материалам ежегодной международной конференции «Диалог» (Москва, 17 июня — 20 июня 2020 г.). Доклады студенческой сессии.

[б.и.], 2020.

RuCLEVR: A Russian Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning

Biryukova K., Chelnokova D., Erkenova J. et al., Communications in Computer and Information Science 2024 Vol. 2364 CCIS P. 109 – 121

Added: February 25, 2026

CausalQA: A Benchmark for Causal Question Answering

Bondarenko A., Wolska M., Heindorf S. et al., , in: Proceedings of the 29th International Conference on Computational Linguistics.: International Committee on Computational Linguistics, 2023. P. 3296–3308.

Added: August 14, 2023

Relying on Discourse Trees to Extract Medical Ontologies from Text

Galitsky B., Ilvovsky D., Goncharova E., , in: Artificial Intelligence. RCAI 2021. Lecture Notes in Computer ScienceVol. 12948.: Springer, 2021. P. 215–231.

Added: October 28, 2021

DaNetQA: a yes/no Question Answering Dataset for the Russian Language

Glushkova T., Machnev A., Fenogenova A. et al., , in: Analysis of Images, Social Networks and Texts: 9th International Conference, AIST 2020, Skolkovo, Moscow, Russia, October 15–16, 2020, Revised Selected PapersVol. 12602.: Springer, 2021. P. 57–68.

Added: November 22, 2020

Russian Q&A Method Study: From Naive Bayes to Convolutional Neural Networks

Nikolaev K., Malafeev A., , in: Analysis of Images, Social Networks and Texts. 7th International Conference AIST 2018.: Springer, 2018. Ch. 12 P. 121–126.

This paper deals with automatic classification of questions in the Russian language. In contrast to previously used methods, we introduce a convolutional neural network for question classification. We took advantage of an existing corpus of 2008 questions, manually annotated in accordance with a pragmatic 14-class typology. We modified the data by reducing the typology to ...

Added: February 15, 2019

Russian-Language Question Classification: a New Typology and First Results

Nikolaev K., Malafeev A., , in: Analysis of Images, Social Networks and Texts. 6th International Conference, 2017, Revised Selected PapersVol. 10716.: Cham: Springer, 2018. Ch. 7 P. 72–81.

This paper deals with automatic classification of questions in the Russian language, a natural early step in building a question answering system. We developed a typology of Russian questions using interrogative particles, pronouns and word order as the main features. A corpus of 2008 questions was manually compiled and annotated according to our typology. We ...

Added: December 1, 2017

Parse thicket representations of text paragraphs

Galitsky B., Ilvovsky D., Kuznetsov S. et al., , in: Компьютерная лингвистика и интеллектуальные технологии: По материалам ежегодной Международной конференции «Диалог» (Бекасово, 29 мая - 2 июня 2013 г.). В 2-х т.Т. 1: Основная программа конференции. Вып. 12 (19).: М.: РГГУ, 2013. P. 239–255.

We develop a graph representation and learning technique for parse structures for sentences and paragraphs of text. We introduce parse thicket as a set of syntactic parse trees augmented by a number of arcs for intersentence word-word relations such as coreference and taxonomies. These arcs are also derived from other sources, including Rhetoric Structure and Speech Act theory. We introduce ...

Added: November 1, 2013