Intelligent question-answering system based on the public political discourse knowledge

2024

Full text Open access: Gold Metadata (CSL-JSON)
DOI 10.1145/3678610.3678613
Data confidence 85 high
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The article describes the implementation of a question-answering system based on knowledge of public political discourse. An ontology of the subject area was developed, a program was developed to publish an answer to a question on the topic of political discourse in the Kazakh language.