Համահեղինակ(ներ):

Hakobyan Levon

Հրատարակության վայրը:

An approach to automated correction of UNL grammar rules for NL-UNL transformations is described. We claim that the development process of the rule sets could be made in a more effective way if some tools are used which can find the rules responsible for the possible errors. In previous articles we already presented such a method for UNL-NL transformations. In the article we present a classification of possible errors applicable for a result of the transformation process from NL to UNL and some modifications of the correction algorithm described in previous publications. An example of the error correction process is also considered.

Նույնականացուցիչ:

oai:noad.sci.am:135949

Լեզու:

English

URL:

լրացուցիչ տեղեկատվություն:

a.avetisyan@undlfoundation.org ; levon.r.hakobyan@gmail.am

Կազմակերպության անվանում:

Institute for Informatics and Automation Problems

Երկիր:

Armenia

Տարի:

2015

Ժամանակահատված:

September 28 - October 2

Գիտաժողովի անվանում:

10 th International Conference on Computer Science and Information Technologies CSIT 2015

Վայր:

Yerevan

Մասնակցության տեսակը:

poster