Co-author(s) :

Hakobyan Levon

Place of publishing:

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.

Identifier:

oai:noad.sci.am:135949

Language:

English

URL:

Additional Information:

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

Affiliation:

Institute for Informatics and Automation Problems

Country:

Armenia

Year:

2015

Time period:

September 28 - October 2

Conference title:

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

Place:

Yerevan

Participation type:

poster