Dependency tree matching with extended Tree edit distance with subtrees for textual entailment

Research output: Chapter in Book/Report/Conference proceedingConference contribution

  • Authors:
  • Maytham Alabbas
  • Allan Ramsay

Abstract

A lot of natural language processing (NLP) applications require the computation of similarities between pairs of syntactic or semantic trees. Tree edit distance (TED), in this context, is considered to be one of the most effective techniques. However, its main drawback is that it deals with single node operations only. We therefore extended TED to deal with subtree transformation operations as well as single nodes. This makes the extended TED with subtree operations more effective and flexible than the standard TED, especially for applications that pay attention to relations among nodes (e.g. in linguistic trees, deleting a modifier subtree should be cheaper than the sum of deleting its components individually). The preliminary results of extended TED with subtree operations were encouraging compared with the standard one when tested on different examples of dependency trees. © 2012 Polish Info Processing Socit.

Bibliographical metadata

Original languageEnglish
Title of host publication2012 Federated Conference on Computer Science and Information Systems, FedCSIS 2012|Fed. Conf. Comput. Sci. Inf. Syst., FedCSIS
PublisherPolish Information Processing Society
Pages11-18
Number of pages7
ISBN (Print)9781467307086
Publication statusPublished - 2012
Event2012 Federated Conference on Computer Science and Information Systems, FedCSIS 2012 - Wroclaw
Event duration: 1 Jul 2012 → …
http://fedcsis.org/proceedings/fedcsis2012/#H4AAIA

Conference

Conference2012 Federated Conference on Computer Science and Information Systems, FedCSIS 2012
CityWroclaw
Period1/07/12 → …
Internet address