A Pilot Study on Automatic Inference Rule Discovery from Turkish Text

Isguder-Sahin G. G., Adali E.

8th IEEE International Conference on Application of Information and Communication Technologies (AICT), Astana, Kazakhstan, 15 - 17 October 2014, pp.268-272 identifier

  • Publication Type: Conference Paper / Full Text
  • City: Astana
  • Country: Kazakhstan
  • Page Numbers: pp.268-272
  • Istanbul Technical University Affiliated: Yes


In this paper we present a framework for extraction of inference rules from Turkish documents, such as "A solved B similar to A found a solution to B". Many natural language processing tasks, such as question answering, information retrieval and machine translation can benefit tremendously from inference rules. Our framework consists of three layers: construction of dependency trees; determining predicates and their complements and finally discovery of inference rules via clustering. We use Silhouette Index (SI) of the clusters as an automatic evaluation metric.