University of Cambridge > Talks.cam > NLIP Seminar Series > Unsupervised Entailment Detection between Dependency Graph Fragments

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Unsupervised Entailment Detection between Dependency Graph Fragments

Download to your calendar using vCal

If you have a question about this talk, please contact Thomas Lippincott .

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.

This talk is part of the NLIP Seminar Series series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Average on weekdays: 9136.24331927 kWh Sidney Sussex College, William Mong Hall, Sidney Street, CB2 3HU BAS Seminar Room 1; https://ukri.zoom.us/j/96200879096

Other talks

Coming soon TBC Talk title TBC Group Work Alicia Anderson discussing some exciting news about HARPS3 Online Causal Inference Seminar
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity