Unsupervised Entailment Detection between Dependency Graph Fragments

Loading...
Thumbnail Image

Date

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

Entailment detection systems are generally designed to work either on single words, relations or full sentences. We propose a new task – detecting entailment between dependency graph fragments of any type – which relaxes these restrictions and leads to much wider entailment discovery. An unsupervised framework is described that uses intrinsic similarity, multi-level extrinsic similarity and the detection of negation and hedged language to assign a confidence score to entailment relations between two fragments. The final system achieves 84.1% average precision on a data set of entailment examples from the biomedical domain.

Keywords

Citation

Endorsement

Review

Supplemented By

Referenced By