A learning-based approach to summarization

Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=q_gF5O3vSoo



Duration: 42:58
22 views
0


Research in summarization has been handicapped by a lack of agreement on how to generate a standard summary (which can serve as a reference in the evaluation of alternative approaches). Part of the problem rests in disagreement between different humans on what constitutes a single good summary. We propose an alternate approach that dispenses with the need for a global reference and instead focuses on the ability of a summarizer to rapidly learn how an individual human summarizes material.




Other Videos By Microsoft Research


2016-09-05Personal Passion and Professional Excellence ΓÇô You canΓÇÖt have one without the other!
2016-09-05Social Mobile Applications, Location, Privacy and the Capital of Nevada [1/16]
2016-09-05Search Engines Considered Harmful: In Search of an Unbiased Web Ranking
2016-09-05Science Friction: Where the Known Meets the Unknown
2016-09-05Concave utility functions on finite sets
2016-09-05Exploring Mars by 4-Wheel Drive
2016-09-05Computing with Selfish Agents [1/2]
2016-09-05Opportunities and Challenges in End-to-End Verification of Software Systems
2016-09-05Tools and Techniques for Prototyping Future Interactions [1/2]
2016-09-05Mathematical Sketching: A New Approach for Creating and Exploring Dynamic Illustrations
2016-09-05A learning-based approach to summarization
2016-09-05Virtual machines: the ultimate tool for computer forensics
2016-09-05Headwinds and Tailwinds:  Where is the U.S. economy going?
2016-09-05Paradigms of Worm Defense & Thoughts from an Ivory Tower
2016-09-05Machine Learning Methods for Discovery of Regulatory Elements in Bacteria
2016-09-05Eyes on Multimodal Interaction
2016-09-05From Promoter to Expression ΓÇô A Probabilistic Framework for Inferring Regulatory Mechanisms
2016-09-05Automated Reconstruction of 3D City Models from Laser Scans and Camera Images
2016-09-05Bergman complexes, Coxeter arrangements, and graph associahedra
2016-09-05Biomal Human Emotion Recognition and Peer Steaming Projects at  Ryerson Multimedia Research Lab
2016-09-05Interfaces for Staying in the Flow         [1/3]



Tags:
microsoft research