Publication Details

Advanced User Interfaces for Semantic Annotation of Complex Relations in Text

DYTRYCH Jaroslav and SMRŽ Pavel. Advanced User Interfaces for Semantic Annotation of Complex Relations in Text. Lecture Notes in Computer Science, vol. 2017, no. 10839, pp. 205-221. ISBN 978-3-319-93581-2. ISSN 0302-9743. Available from: https://www.springer.com/us/book/9783319935805
Czech title
Pokročilá uživatelská rozhraní pro sémantické anotování komplexních vztahů v textu
Type
journal article
Language
english
Authors
URL
Keywords
computer-assisted tagging, text annotation, ambiguous entity
names
Abstract
This paper deals with computer-assisted semantic annotation of text. It particularly focuses on the annotation of complex relations and linking of entities with highly ambiguous names. These tasks cannot be reliably accomplished by fully automatic methods today. Our research explores user interface features that can help the manual annotation process. We extend our original experiments published in the Interaction Patterns in Computer-assisted Semantic Annotation of Text - An Empirical Evaluation by a detailed analysis of advantages brought by the semantic filtering feature of our 4A annotation system. We also expand our user study on the annotation of highly ambiguous entities showing speed-ups brought by a presentation mode for entity candidates employing advanced disambiguation contexts.
Published
2018
Pages
205-221
Journal
Lecture Notes in Computer Science, vol. 2017, no. 10839, ISSN 0302-9743
Book
Agents and Artificial Intelligence
ISBN
978-3-319-93581-2
Publisher
Springer International Publishing
DOI
BibTeX
@ARTICLE{FITPUB11404,
   author = "Jaroslav Dytrych and Pavel Smr\v{z}",
   title = "Advanced User Interfaces for Semantic Annotation of Complex Relations in Text",
   pages = "205--221",
   booktitle = "Agents and Artificial Intelligence",
   journal = "Lecture Notes in Computer Science",
   volume = 2017,
   number = 10839,
   year = 2018,
   publisher = "Springer International Publishing",
   ISBN = "978-3-319-93581-2",
   ISSN = "0302-9743",
   doi = "10.1007/978-3-319-93581-2\_11",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11404"
}
Back to top