Unsupervised Entailment Detection between Dependency Graph Fragments
| dc.creator | Rei, M | |
| dc.creator | Briscoe, T | |
| dc.date | 2018-03-22T16:20:45Z | |
| dc.date | 2018-03-22T16:20:45Z | |
| dc.date | 2011-06-23 | |
| dc.date.accessioned | 2026-08-03T03:07:56Z | |
| dc.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. | |
| dc.format | application/pdf | |
| dc.identifier | https://www.repository.cam.ac.uk/handle/1810/274250 | |
| dc.identifier | 10.17863/CAM.21358 | |
| dc.identifier.uri | https://repo.dare.co.zw/handle/123456789/173143 | |
| dc.language | eng | |
| dc.title | Unsupervised Entailment Detection between Dependency Graph Fragments | |
| dc.type | Conference Object |