Dolgoročni cilj projekta Obeliks je izdelava in nadgrajevanje najbolj natančnega statističnega označevalnika za slovenski jezik. Oblikoskladenjsko označevanje je proces pripisovanja oblikoslovnih (in deloma skladenjskih) lastnosti besedam v poljubnem besedilu. Tako označeno besedilo je predpogoj za delovanje večine aplikacij, ki temeljijo na analizi naravnega jezika. Označevanje slovenskih besedil je zelo težak problem, saj mora algoritem za označevanje pravilno izbirati med skoraj dva tisoč oznakami (število različnih oznak za označevanje angleškega besedila je zgolj okoli šestdeset). Izvorna koda je na GitHub-u (glej Wiki). // The aim of the Obeliks project is to develop the most accurate statistical tagger for the Slovene language. Morphosyntactic tagging is the process of categorizing a word in a text into a particular part of speech category and describing it with various morphological features related to that category. The source code is on GitHub (see Wiki).

Project Activity

See All Activity >

Categories

Linguistics

License

MIT License

Follow Obeliks

Obeliks Web Site

Other Useful Business Software
Build Agents and Models on One Platform Icon
Build Agents and Models on One Platform

Everything you need to build production-ready agents and models. Access 200+ Google and third-party AI models and tools.

Gemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
Try It Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of Obeliks!

Additional Project Details

Operating Systems

Windows

Intended Audience

Advanced End Users, Developers, End Users/Desktop, Information Technology, Science/Research

User Interface

.NET/Mono, Command-line, Web-based

Programming Language

C#

Related Categories

C# Linguistics Software

Registered

2012-05-05