Using FCA and Concept Explications for Finding an Appropriate Concept

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F47813059%3A19240%2F21%3AA0000920" target="_blank" >RIV/47813059:19240/21:A0000920 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/61989100:27240/21:10248836

Výsledek na webu

<a href="https://nlp.fi.muni.cz/raslan/raslan21.pdf" target="_blank" >https://nlp.fi.muni.cz/raslan/raslan21.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Using FCA and Concept Explications for Finding an Appropriate Concept

Popis výsledku v původním jazyce

This paper introduces the method of discovering a plausible atomic concept that corresponds to the generated molecular concept explication and known attributes’ values and properties of objects falling under the concept. First, we summarize the process of concept explication via the symbolic method of supervised machine learning from formalized natural language sentences. To obtain particular concept explications, we exploit heuristic procedures that operate on the symbolic representation of current hypothesis and example to obtain particular concept explications. These explications serve as descriptions of the sought atomic concept accordingly to the given text sources. Afterwards, the method of searching for the appropriate concept based on attributes’ values is outlined. Thus, user can seek a specific concept, which can be vague or inaccurate, among the so-extracted explications. We focus on a situation in which the user knows basic properties or attributes’ values and searches for a suitable atomic concept that is described by these properties or attributes’ values. To explain the process, we summarize the creation of explications and the method of Formal Concept Analysis (FCA) as a theoretical background. As a result, we present to the user an appropriate atomic concept. The whole method is demonstrated by a few examples.

Název v anglickém jazyce

Using FCA and Concept Explications for Finding an Appropriate Concept

Popis výsledku anglicky

This paper introduces the method of discovering a plausible atomic concept that corresponds to the generated molecular concept explication and known attributes’ values and properties of objects falling under the concept. First, we summarize the process of concept explication via the symbolic method of supervised machine learning from formalized natural language sentences. To obtain particular concept explications, we exploit heuristic procedures that operate on the symbolic representation of current hypothesis and example to obtain particular concept explications. These explications serve as descriptions of the sought atomic concept accordingly to the given text sources. Afterwards, the method of searching for the appropriate concept based on attributes’ values is outlined. Thus, user can seek a specific concept, which can be vague or inaccurate, among the so-extracted explications. We focus on a situation in which the user knows basic properties or attributes’ values and searches for a suitable atomic concept that is described by these properties or attributes’ values. To explain the process, we summarize the creation of explications and the method of Formal Concept Analysis (FCA) as a theoretical background. As a result, we present to the user an appropriate atomic concept. The whole method is demonstrated by a few examples.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of Recent Advances in Slavonic Natural Language Processing, RASLAN 2021,

ISBN

9788026316701

ISSN

2336-4289

e-ISSN

—

Počet stran výsledku

12

Strana od-do

49-60

Název nakladatele

Tribun EU

Místo vydání

Brno

Místo konání akce

Karlova Studánka

Datum konání akce

10. 12. 2021

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—