Skip to content
You are not logged in |Login  
     
Limit search to available items
Record:   Prev Next
Resources
More Information
Bestseller
BestsellerE-book
Author Thoma, Steffen, author.

Title Multi-modal data fusion based on embeddings / Steffen Thomas, FZI Forschungszentrum Informatik, Karslruhe, Germany.

Publication Info. Amsterdam : IOS Press, [2019]
©2019

Item Status

Description 1 online resource.
Physical Medium polychrome
Description text file
Series Studies on the Semantic Web ; volume 041
Studies on the Semantic Web ; volume 041.
Bibliography Includes bibliographical references.
Summary Many web pages include structured data in the form of semantic markup, which can be transferred to the Resource Description Framework (RDF) or provide an interface to retrieve RDF data directly. This RDF data enables machines to automatically process and use the data. When applications need data from more than one source the data has to be integrated, and the automation of this can be challenging. Usually, vocabularies are used to concisely describe the data, but because of the decentralized nature of the web, multiple data sources can provide similar information with different vocabularies, making integration more difficult. This book, Multi-modal Data Fusion based on Embeddings, describes how similar statements about entities can be identified across sources, independent of the vocabulary and data modeling choices. Previous approaches have relied on clean and extensively modeled ontologies for the alignment of statements, but the often noisy data in a web context does not necessarily adhere to these prerequisites. In this book, the use of RDF label information of entities is proposed to tackle this problem. In combination with embeddings, the use of label information allows for a better integration of noisy data, something that has been empirically confirmed by experiment. The book presents two main scientific contributions: the vocabulary and modeling agnostic fusion approach on the purely textual label information, and the combination of three different modalities into one multi-modal embedding space for a more human-like notion of similarity. The book will be of interest to all those faced with the problem of processing data from multiple web-based sources.
Contents Intro; Title Page; Introduction; Motivation; Challenges; Hypotheses and Research Questions; Contributions; Outline; Foundations; Semantic Web; Representation Learning; Data Fusion; Introduction; Motivating Example; Related Work; Pipeline; Experiments; Summary; Multi-modal Fusion and Transfer; Introduction; Motivating Example; Related Work; Multi-modal Fusion; Experiments on Multi-modal Fusion; Multi-modal Transfer; Experiments on Multi-modal Transfer; Summary; Conclusion; Summary; Future Work; Bibliography; Appendix; Full Michael Jordan Example; Evaluation Tables; Evaluation Heatmaps
Local Note eBooks on EBSCOhost EBSCO eBook Subscription Academic Collection - North America
Subject RDF (Document markup language)
RDF (Document markup language)
Semantic Web.
Semantic Web.
Genre/Form Electronic books.
Other Form: Print version: Thoma, Steffen. Multi-modal data fusion based on embeddings. Amsterdam : IOS Press, [2019] 1643680285 9781643680286 (OCoLC)1127843339
ISBN 9781643680293 (electronic book)
1643680293 (electronic book)
9781643680286
1643680285