|
METHOD AND APPARATUS FOR AUTOMATED LINGUISTIC ONTOLOGY EXTENSION BY USING GOOGLE NGRAMS
|
|
|
D. Nochevnoi; S. Klimenkov; E. Tsopa
|
|
|
||
|
|
|
|
1314-2704
|
|
|
||
|
English
|
|
|
21
|
|
|
7.1
|
|
|
• Prof. DSc. Oleksandr Trofymchuk, UKRAINE
• Prof. Dr. hab. oec. Baiba Rivza, LATVIA |
|
|
||
|
Extracting information from a text is an undivided part of modern NLP applications. Ontologies and semantic networks play important role in sense disambiguation problem, helping us distinguish concept nodes in text inputs. As we know, every language is always changing. Each generation of people adds something new to it, and new terms and word forms emerge while others become deprecated and people stop using them. Therefore modern linguistic ontologies have to store this information within a concept node. In this paper the brief overview for the state of the art in the sphere of temporal databases is presented. Authors nowadays tend to implement temporal knowledge bases for their purposes and successfully use it. There are several remarkable examples of production ready systems with temporal properties provided. In this paper it is suggested to implement temporal properties for the ontology, developed by the authors in previous works. At least, each concept or term in the ontology should contain the information about the start and the end of its existence. Google Ngram Viewer was used to provide information about concepts or terms frequencies by year based on a text corpus which includes many books (even in Russian) from the year 1500 to nowadays. A new method and apparatus for automated linguistic ontology extension is proposed. A proof of concept was implemented during this work and the existing ontology was expanded with temporal fields by using Google Ngrams. The next step will be fulfilling all missed dates in our database by means of this approach.
|
|
|
conference
|
|
|
||
|
||
|
21st International Multidisciplinary Scientific GeoConference SGEM 2021
|
|
|
21st International Multidisciplinary Scientific GeoConference SGEM 2021, 16 - 22 August, 2021
|
|
|
Proceedings Paper
|
|
|
STEF92 Technology
|
|
|
SGEM International Multidisciplinary Scientific GeoConference
|
|
|
SWS Scholarly Society; Acad Sci Czech Republ; Latvian Acad Sci; Polish Acad Sci; Serbian Acad Sci & Arts; Natl Acad Sci Ukraine; Natl Acad Sci Armenia; Sci Council Japan; European Acad Sci, Arts & Letters; Acad Fine Arts Zagreb Croatia; Croatian Acad Sci
|
|
|
101-108
|
|
|
16 - 22 August, 2021
|
|
|
website
|
|
|
cdrom
|
|
|
7867
|
|
|
linguistic ontology; semantic network; temporal database; semantic relation; knowledge base
|
|