Detail publikace

Advanced User Interfaces for Semantic Annotation of Complex Relations in Text

DYTRYCH, J. SMRŽ, P.

Originální název

Advanced User Interfaces for Semantic Annotation of Complex Relations in Text

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

computer-assisted tagging, text annotation, ambiguous entity names

Autoři

DYTRYCH, J.; SMRŽ, P.

Vydáno

3. 2. 2018

Nakladatel

Springer International Publishing

Místo

Cham

ISBN

978-3-319-93581-2

Kniha

Agents and Artificial Intelligence

Edice

Lecture Notes in Computer Science

ISSN

0302-9743

Periodikum

Lecture Notes in Computer Science

Ročník

10839

Číslo

2018

Stát

Spolková republika Německo

Strany od

205

Strany do

221

Strany počet

17

URL

BibTex

@inproceedings{BUT154987,
  author="Jaroslav {Dytrych} and Pavel {Smrž}",
  title="Advanced User Interfaces for Semantic Annotation of Complex Relations in Text",
  booktitle="Agents and Artificial Intelligence",
  year="2018",
  series="Lecture Notes in Computer Science",
  journal="Lecture Notes in Computer Science",
  volume="10839",
  number="2018",
  pages="205--221",
  publisher="Springer International Publishing",
  address="Cham",
  doi="10.1007/978-3-319-93581-2\{_}11",
  isbn="978-3-319-93581-2",
  issn="0302-9743",
  url="https://www.springer.com/us/book/9783319935805"
}