TU Darmstadt / ULB / TUbiblio

What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer

Rohrbach, Marcus and Stark, Michael and Szarvas, György and Schiele, Bernt and Gurevych, Iryna (2010):
What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer.
In: Proceedings of the 23rd IEEE Conference on Computer Vision and Pattern Recognition, [Online-Edition: https://ieeexplore.ieee.org/document/5540121/],
[Conference or Workshop Item]

Abstract

Remarkable performance has been reported to recognize single object classes. Scalability to large numbers of classes however remains an important challenge for today’s recognition methods. Several authors have promoted knowledge transfer between classes as a key ingredient to address this challenge. However, in previous work the decision, which knowledge to transfer has required either manual supervision or at least a few training examples limiting the scalability of these approaches. In this work we explicitly address the question of how to automatically decide which information to transfer between classes without the need of any human intervention. For this we tap into linguistic knowledge bases to provide the semantic link between sources (what) and targets (where) of knowledge transfer. We provide a rigorous experimental evaluation of different knowledge bases and state-of-the-art techniques from Natural Language Processing which goes far beyond the limited use of language in related work. We also give insights into the applicability (why) of different knowledge sources and similarity measures for knowledge transfer.

Item Type: Conference or Workshop Item
Erschienen: 2010
Creators: Rohrbach, Marcus and Stark, Michael and Szarvas, György and Schiele, Bernt and Gurevych, Iryna
Title: What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer
Language: English
Abstract:

Remarkable performance has been reported to recognize single object classes. Scalability to large numbers of classes however remains an important challenge for today’s recognition methods. Several authors have promoted knowledge transfer between classes as a key ingredient to address this challenge. However, in previous work the decision, which knowledge to transfer has required either manual supervision or at least a few training examples limiting the scalability of these approaches. In this work we explicitly address the question of how to automatically decide which information to transfer between classes without the need of any human intervention. For this we tap into linguistic knowledge bases to provide the semantic link between sources (what) and targets (where) of knowledge transfer. We provide a rigorous experimental evaluation of different knowledge bases and state-of-the-art techniques from Natural Language Processing which goes far beyond the limited use of language in related work. We also give insights into the applicability (why) of different knowledge sources and similarity measures for knowledge transfer.

Title of Book: Proceedings of the 23rd IEEE Conference on Computer Vision and Pattern Recognition
Uncontrolled Keywords: Semantic Information Management;UKP_a_SIM
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Ubiquitous Knowledge Processing
Date Deposited: 31 Dec 2016 14:29
Official URL: https://ieeexplore.ieee.org/document/5540121/
Identification Number: TUD-CS-2010-0079
Related URLs:
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item