Slovenščina.eu

Povratne informacije

davidb — Tue, 15 Nov 2022 22:05:19 +0000

Feedback davidb Tue, 12/06/2022 - 22:17

Do you have any suggestions? Comments? Ideas? We would be glad to hear from you.

We develop tools for you and your opinion matters greatly to us.

Kazalniki

davidb — Wed, 09 Nov 2022 11:25:05 +0000

Results davidb Tue, 12/06/2022 - 22:01

KAZALNIK	REZULTAT	GITHUB	CLARIN.SI	DEMO	Wiki
K1.1 - Nadgrajeni odprto dostopni jezikovni viri (korpusni in leksikonski) na repozitoriju CLARIN.SI.	učni korpus		SUK 1.0 - standardna slovenščina Janes-Tag 3.0 - nestandardna slovenščina
	SuperGLUE	Povezava	Povezava
	učna množica Janes-Norm		Povezava
	leksikon Sloleks		Povezava
	govorni korpus GOS
	korpus siParl		Povezava
K1.2 - Novi jezikovni viri, dostopni v obstoječih konkordančnikih (CLARIN.SI, viri.cjvt.si)	GOS 2.0			Na voljo januarja 2023
	Šolar 3.0		Povezava	Konkordančnik KonText, besedila učencev Konkordančnik KonText, učiteljski popravki
	siParl 3.0			Na voljo januarja 2023
	Metakorpus vseh večjih slovenskih korpusov		Povezava	Konkordančnik KonText Konkordančnik NoSketch Engine
K1.3 - Št. temeljnih jez. virov za slo. (korpusnih in leksikonskih z razvito infra.) za učinkovit in kontinuiran razvoj	Gigafida				Na voljo februarja 2023
	Janes				Na voljo februarja 2023
	GOS				Na voljo februarja 2023
	Šolar				Na voljo februarja 2023
	KOST				Na voljo februarja 2023
	Sloleks				Na voljo februarja 2023
	Učni korpus				Na voljo februarja 2023
	SuperGLUE				Na voljo februarja 2023
	Metakorpus				Na voljo februarja 2023
K1.4 - Nova programska orodja za strojno in ročno označevanje slo. besedil na različnih nivojih	cevovod za označevanje slovenščine	Povezava	Povezava	Povezava
	program za anotacijo jezikovnih napak			Testna različica
	program za anotacijo slovenskih parlamentarnih razprav
	program za popravljanje strojno izluščenih podatkov specifično za leksikon Sloleks			Povezava
K2.1 - Št. ur dostopnih govornih baz na način CC BY-SA za razpoznavalnik tekočega govora v slovenščini	govorna baza za razpoznavalnik govora		Transkripcije Avdio
K2.2 - Št. podpornih orodij za izdelavo in uporabo razpoznavalnika slovenskega govora	akustični normalizator	Povezava
	sintaktični normalizator	Povezava	Povezava
	sintaktični denormalizator	Povezava	Povezava
	orodje za pretvorbo grafemov v foneme	Povezava
	orodje za postavljanje ločil v surovi tekst	Povezava	Povezava Povezava
K2.3 - Razpozavalnik slovenskega govora	razpoznavalnik slovenskega govora	Povezava	Povezava Povezava	Povezava
K3.1 - Izdelava digitalne slovarske baze in smernic za splošno orodje za procesiranje besedil	podatkovni model z vsebovanimi podatki virov, ki bodo skupaj predstavljali digitalno slovarsko bazo				Povezava
	zasnova orodja in smernice za gradnjo interoperabilnih semantičnih tehnologij
K3.2 - Semantična mreža in podporna orodja za ekstrakcijo pomenskih delov iz besedil	orodje za prepoznavanje imenskih entitet	Povezava	Povezava	Povezava
	orodje za odkrivanje koreferenčnosti	Povezava	Povezava	Povezava
	orodje za ekstrakcijo povezav	Povezava	Model v repozitoriju kode Korpus	Povezava
	orodje za avtomatsko ekstrakcijo semantične mreže	Povezava		Povezava
	orodje za avtomatsko zgrajeno semantično mrežo (vir)	Povezava
K3.3 - Št. naprednih semantičnih orodij	orodje za izračun vektorskih vložitev BERT hkrati z njihovim obračunom in objavo	Povezava	Povezava
	izdelava orodij za razdvoumljanje	Povezava	Povezava	Povezava
	prepoznavanje semantičnih premikov in diahronih analiz	Povezava	Povezava	Semantični premiki 2017-2018 Semantični premiki 1997-2018 Semantični premiki 1997-2002-2007-2013-2018
	avtomatsko povzemanje krajših in daljših besedil	Povezava	Povezava	Povezava
	avtomatsko odgovarjanje na vprašanja	Povezava	Povezava	Povezava
K4.1 - Obseg dvojezičnih besedil dostopnih na način CC BY-SA za strojni prevajalnik za jezikovni par SL-AN in AN-SL	obseg dvojezičnih besedil dostopnih na način CC BY-SA za strojni prevajalnik za jezikovni par SL-AN in AN-SL		Povezava
K4.2 - Št. podpornih orodij za izdelavo in uporabo strojnega prevajalnika za jezikovni par SL-AN in AN-SL	Št. podpornih orodij za izdelavo in uporabo strojnega prevajalnika za jezikovni par SL-AN in AN-SL	Povezava
	prevajalnik	Povezava	Povezava Povezava	Povezava
K5.1 - Terminološki portal z vgrajeno infrastrukturo za samostojno izdelavo terminoloških virov in luščilnikom	terminološki portal z vgrajeno infrastrukturo za samostojno izdelavo terminoloških virov in luščilnikom	Povezava		Povezava Povezava
K5.2 - Št. odprtodost. term. virov, namenjenih za jezikovno tehnološko obdelavo, deponiranih v repozitorij Clarin.si	Davčni terminološki slovar		Povezava
	Terminološki slovar elektronskega kajenja		Povezava
	Glosar s področja konjeništva		Povezava
	Vojaški slovar študentov obramboslovja		Povezava
	Terminološki slovar s področja umetne inteligence		Povezava
	Glosar akademske integritete		Povezava
	Slovensko-angleški pojmovnik s področja vzgoje in izobraževanja		Povezava
K5.3 - Odprtodostopni urejevalnik za izdelavo terminoloških virov	odprtodostopni urejevalnik za izdelavo terminoloških virov	Povezava
K5.4 - Št. slovarjev, pretvorjenih v standardni format in integriranih v terminološki portal	Davčni terminološki slovar			Povezava
	Terminološki slovar elektronskega kajenja			Povezava
	Glosar s področja konjeništva			Povezava
	Vojaški slovar študentov obramboslovja			Povezava
	Računalniški terminološki slovar			Povezava
	Glosar akademske integritete			Povezava
	Slovensko-angleški pojmovnik s področja vzgoje in izobraževanja			Povezava
K5.5 - Odprtokodno orodje za samodejno luščenje terminologije, vgrajeno v terminološki portal	Odprtokodno orodje za samodejno luščenje terminologije, vgrajeno v terminološki portal	Povezava
K5.6 - Smernice in navodila za izdelavo terminološkiih virov	smernice in navodila za izdelavo terminoloških virov
K6.1 - Sheme za validacijo virov	sheme za validacijo virov	Povezava		Povezava Povezava
K6.2 - Tehnično brezhibni jezikovni viri projekta, arhivirani v repozitorij CLARIN.SI	Tehnično brezhibni jezikovni viri projekta, arhivirani v repozitorij CLARIN.SI		Povezava
K6.3 - Postavitev korpusov pod konkordančnike CLARIN.SI	Postavitev korpusov pod konkordančnike CLARIN.SI			Povezava
K7.1 - Odkupljeni jezikovni viri ali jezikovni podatki	Odkupljeni jezikovni viri ali jezikovni podatki			Povezava
K7.2 - Aktivna spletna stran projekta	aktivna spletna stran projekta			Povezava
K7.3 - Zaključna konferenca projekta	zaključna konferenca projekta			Povezava

Listed and linked below, you can access the project results (in Slovene).

Nova spletna stran

davidb — Wed, 25 Nov 2020 21:25:14 +0000

New website davidb Mon, 04/12/2021 - 19:49

New website The project Development of Slovene in a Digital Environment has a new website. On it you will find all the information about the project, project partners and the dynamics of our work, and we will also keep you informed about current project activities.

RSDO News

Podpis pogodbe

davidb — Wed, 25 Nov 2020 21:07:51 +0000

Contract signed davidb Mon, 04/12/2021 - 19:47

On 17 November 2020, a contract was signed for financing the project Development of Slovene in a Digital Environment, between the University of Ljubljana and the Ministry of Culture of the Republic of Slovenia.

In this way, the project was financed by the European Structural and Investment Funds. The project was selected for funding on April 22, 2020, and work on the project began in May of the same year.

RSDO News

Politika piškotkov

developer — Fri, 23 Oct 2020 20:04:36 +0000

Cookies policy davidb Mon, 04/12/2021 - 19:35

This website uses cookies. These are small data files that the web server offers to your browser when you visit – they are usually stored on your computer or other electronic device (mobile phone, tablet …) in order to ensure efficient browsing of the website, perform certain functions and enable web pages to remember certain user settings. Cookies are used to store settings, manage the session of an individual user, differentiate between users and to track them on a website (or several websites).

Cookies are divided according to functions, some of which are required for the operation of the website. Without these cookies, certain services you want to use on this website would not work properly, so they will always be installed.

Functional cookies are the ones that help a website remember your selected settings. You edit the installation according to your own preferences.

Analytical cookies are those that record the activities of visitors on our website. We use the service for the purpose of analysing traffic (counting visitors, identifying browsers and user time spent on the page, navigation problems, etc.). With the help of these cookies, it is easier to develop a website tailored to your needs and improve the user experience.

Advertising and profiling cookies are cookies of third parties (e.g., Facebook, YouTube, Google …) that anonymously collect data on website visits. They are used by advertisers to show ads that they think are relevant to the visitor.

Cookies are distinguished according to the following characteristics:

temporary (session) or permanent cookies,
own cookies or third party cookies.

A session cookie is a cookie that is automatically deleted when you close your browser, while a permanent cookie remains stored in your browser until a certain period of time has elapsed (which can be minutes, days, or years).

Own cookies are set by the website you have visited, and third-party cookies are set by an external partner web service, which is included in the website due to the desired functionality.

What cookies do we use on this website?

List of cookies on this website:

Required (always enabled):

Service	Cookie name (browser storage time)	Description
Website	has_js session_api_session	These cookies are important for the operation of the website and will always be present.
Enki Cookie Control	cookieconsent_status (1 year) cookieconsent_group2 (1 year) cookieconsent_group3 (1 year)	These cookies are used to store information about the settings related to the use of cookies on the site and will always be present.

Functional:

Service	Cookie name (browser storage time)	Description
Piškotki storitve YouTube	Demographics (6 months) ACTIVITY (until session end) use_hitbox (until session end) PREF (10 years) VISITOR_INFO1_LIVE (8 months) YSC (until session end)	YouTube videos are placed on the website in a so-called privacy policy mode. This mode does not install any cookies until you press the play button. Once you start playing the clip, YouTube may install a cookie, but the information does not breach your privacy.

Analytical:

Service	Cookie name (browser storage time)	Description
Google Analytics	_ga (2 years) _gat (1 minute) _gid (1 day)	These cookies are intended to collect information about the use of the website. They allow us to analyze the sessions, with which we can improve the user experience. Data is collected in an anonymous form. You can read more about Google's data protection here. These cookies will only be installed after you have agreed to their use.

Service

Cookie name (browser storage time)

Description

Google Analytics

_ga (2 years)
_gat (1 minute)
_gid (1 day)

These cookies are intended to collect information about the use of the website. They allow us to analyze the sessions, with which we can improve the user experience. Data is collected in an anonymous form.

You can read more about Google's data protection here.

These cookies will only be installed after you have agreed to their use.

Pravno obvestilo

developer — Fri, 23 Oct 2020 08:10:06 +0000

Legal notice davidb Mon, 04/12/2021 - 19:27

The holder of copyright and related rights on this website is the University of Ljubljana. This website is licensed under an Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) Creative Commons License. Users are permitted to reproduce, distribute, adapt, and process the original or derivative work of the work, provided that they identify the author of the work and disseminate the work / further adaptation under the same conditions.

The authors of the website strive for the up-to-dateness, accuracy and completeness of all data and information on the website, but do not assume any responsibility for their actual up-to-dateness, accuracy and completeness. Users access the site at their own risk. The authors are not responsible for any damage due to disturbed or disabled use of the website or for any errors or omissions in its content.

The authors also do not assume any responsibility for the content and operation of the sites linked to this site. The authors reserve the right to change the website at any time without prior notice, both in terms of content and design.

404

developer — Fri, 02 Aug 2019 12:43:25 +0000

404 davidb Mon, 04/12/2021 - 19:21

About the project

With the project titled Development of Slovene in a Digital Environment (DSDE), which is financed by the Slovenian Ministry of Culture, and the European Regional Development Fund, Slovenia has recognized the importance of developing modern language technologies for the Slovene language.

Razvoj slovenščine v digitalnem okolju

developer — Fri, 23 Oct 2020 12:58:53 +0000

Development of Slovene in a Digital Environment davidb Mon, 04/12/2021 - 17:35

The development of language technologies is crucial for the survival of a language in the digital age.

About the project

With the project titled Development of Slovene in a Digital Environment (DSDE), which is financed by the Slovenian Ministry of Culture, Slovenia has recognized the importance of developing modern language technologies for the Slovene language.

MORE ABOUT THE PROJECT

Project goals

The project goal is to meet the needs for computational tools and services in the field of language technologies for Slovene.

WORK PACKAGES

Kazalniki

Dostopajte do rezultatov projekta.

Povezava do rezultatov

Text collection

Would you like to help us with text collection and contribute to the development of Slovene in a digital environment?

Contribute texts

Project partners

The consortium is comprised of twelve institutions, which are some of the largest educational and research organizations in Slovenia – three universities, three public research organizations, and six companies.

MEET THE PARTNERS

About us

Each work package of the project is led by experts in the field of linguistics and computer science.

MEET US

Projektni sklopi

developer — Tue, 20 Oct 2020 10:22:09 +0000

Work packages davidb Mon, 04/12/2021 - 17:30

The end products will help to communicate, collaborate, do business, share knowledge, participate in social and political discourse in a user-friendly way, and contribute to overcoming linguistic hurdles.

Language resources

In the first work package, we will upgrade Slovenian text corpora and the lexicon of word forms. We will renew training datasets and procedures for automatic linguistic annotation of modern Slovene. The results will be refreshed and expanded language resources available to both the user community and for the purposes of machine learning. The developed procedures and tools will make for a faster and easier update of Slovenian corpora in the future.

Speech technologies

It is planned to create a speech database, which will be the foundation for the development of a general speech recognizer, support tools and procedures to further develop a robust general and specialized recognizer, a web portal containing support tools and recognition models. Additionally, we will prepare guidelines for the creation of a real-time recognizer for the education domain.

Semantic resources and technologies

Objectives include the creation of a central open-access digital dictionary database, which combines different types of linguistic data for Slovene, the automatic creation of a semantic network, development of resources and tools for word sense disambiguation and semantic shift recognition, tools for automatic summarization and question answering, and the creation of corpora for performing semantic analyses.

Machine translation

The goals of this work package include the deployment of a reference machine translation engine, the development of support tools and definition of evaluation methods, the testing of alternative neural machine translation (NMT) frameworks, the development of NMT models and their upgrades in light of future updates to the corpus of translations, the development of a web portal, which will host the translation service, the preparation of a long-term plan for developing a MT engine for the education domain, a plan for further development of the general MT engine, and the collection of texts for the corpus of translations.

Terminology portal

This work package consists of the creation of a terminology portal with an accompanying search engine capable of searching through terminological resources, an online concordancer for the analysis of specialized corpora, tools for terminological candidates extraction, an online terminological resources editor, various guidelines and instructions for compiling terminological resources with sample databases, the deployment of a terminology consultancy centre, which will help users resolving queries, the answers to which will be readily published. We will also prepare a plan for future development and upgrading of the terminology portal after the completion of the project.

Maintenance of the infrastructure centre for language resources and technologies

The goals are to provide existing and upgraded CLARIN.SI infrastructure services, to ensure the development and maintenance of XML schemas, the distribution of language resources and tools, to ensure the acquisition of existing language resources, and to inform end users about the project results.

The project aim is to meet the needs for computational tools and services in the field of language technologies for the Slovenian language, to be used by research organizations, companies, and the general public.

About the project

Partners

About the project

More about the project

Partnerji

developer — Tue, 20 Oct 2020 08:23:08 +0000

Partners davidb Mon, 04/12/2021 - 17:23

University of Ljubljana

The University of Ljubljana is the coordinator of the consortium. Five faculties who founded the Centre for Language Resources and Technologies are participating in the project: the Faculty of Computer and Information Science, the Faculty of Electrical Engineering, the Faculty of Arts, the Faculty of Social Sciences and the Faculty of Education. They are joined by the Faculty of Public Administration.

VISIT THE UL WEBSITE

University of Maribor

The project involves the faculties of Electrical Engineering, Computer Science and Informatics, Education and Organizational Sciences.

VISIT THE UM WEBSITE

University of Nova Gorica

The University of Nova Gorica is represented by the Faculty of Humanities.

VISIT THE UNG WEBSITE

Jožef Stefan Institute

Two units of the Jožef Stefan Institute are involved in the project: The Department of Knowledge Technologies and the Laboratory for Artificial Intelligence, both of which manage the CLARIN.SI infrastructure at the JSI. CLARIN.SI is part of the European infrastructure CLARIN ERIC, which is in itself part of the European infrastructures ESFRI and as such will be receiving long-term support.

VISIT THE JSI WEBSITE

Scientific Research Centre of the Slovenian Academy of Sciences and Arts

https://www.fran.si/

The Fran Ramovš Institute for the Slovene Language, a central institution dedicated to the systematic monitoring and interpretation of Slovene language material, which maintains the Fran dictionary portal as part of its research infrastructure, is participating in the project representing the Scientific Research Centre of the Slovenian Academy of Sciences and Arts. SASA, together with JSI, is also part of the second ESFRI infrastructure in the field of humanities, DARIAH-SI. The Institute of Recent History coordinates this infrastructure in Slovenia.

VISIT THE SASA WEBSITE

Institute of Contemporary History

The Institute of Contemporary History is a research institution hailing a sixty-year tradition of continuous research into contemporary history and publishing. The Institute coordinates the ESFRI infrastructure in the field of humanities in Slovenia – DARIAH-SI.

VISIT THE ICH WEBSITE

Alpineon

Alpineon is a high-tech company that operates in the field of language resources and technologies and specializes in speech technologies, biometric and imaging technologies.

VISIT THE ALPINEON WEBSITE

Amebis

Since being founded in 1991, Amebis has been developing language resources and technologies, especially for Slovene, while also being involved in electronic publishing.

VISIT THE AMEBIS WEBSITE

Aikwit

The young company Aikwit works in the field of providing translation services.

VISIT THE AIKWIT WEBSITE

Vitasis

The company Vitasis operates in the field of information technology.

Slovenian Press Agency

The Slovenian Press Agency (STA) is an important user of newly developed language technology products and is primarily involved in the project as a product evaluator and disseminator of project results.

VISIT THE STA WEBSITE

Post of Slovenia

As a user of the products developed within the project, the Post of Slovenia primarily acts as their evaluator and promoter.

VISIT THE PS WEBSITE

The consortium consists of twelve institutions, including the largest educational and research organizations in Slovenia – three universities, three public research organizations, and six companies.

About the project

More about the project