Ralf Krestel

• About Me
• Publications
  • Book Chapters
  • Journal Articles
  • Conference Papers
  • Workshop Papers
    • PST 21
    • LCHANGE 21
    • WOAH 21
    • ESIDA 21
    • FAPER 20
    • LWDA 20
    • TRAC 20a
    • TRAC 20b
    • AI4HI 20
    • GermEval 19
    • MIDAS 19
    • TRAC 18a
    • ALW 18
    • GermEval 18
    • TRAC 18b
    • DSMM 18
    • BigVis 18
    • LWDA 17a
    • LWDA 17b
    • DSMM 17
    • LWDA 16
    • Q4APS 16
    • SBD 16
    • LWA 15
    • TempWeb 15
    • ENRICH 13
    • NLPFrame 10
    • TAC 09
    • DC 09
    • TAC 08
    • RSDC 08
    • LaTeCH 08
    • DUC 07
    • DUC 06
    • SD 05
    • DUC 05
  • Posters & Demos
  • Proceedings
  • Others
• Travels

LWDA 17a

Uncovering Business Relationships: Context-sensitive Relationship Extraction for Difficult Relationship Types

Abstract

This paper establishes a semi-supervised strategy for extracting various types of complex business relationships from textual data by using only a few manually provided company seed pairs that exemplify the target relationship. Additionally, we offer a solution for determining the direction of asymmetric relationships, such as “ownership of”. We improve the reliability of the extraction process by using a holistic pattern identification method that classifies the generated extraction patterns. Our experiments show that we can accurately and reliably extract new entity pairs occurring in the target relationship by using as few as five labeled seed pairs.

Full Paper

LWDA17a.pdf

Workshop Homepage

LWDA 2017

BibTex Entry

@InProceedings{krestel-lwda17a, author = {Zhe Zuo and Michael Loster and Ralf Krestel and Felix Naumann}, title = {{Uncovering Business Relationships: Context-sensitive Relationship Extraction for Difficult Relationship Types}}, booktitle = {{Proceedings of the Conference "Lernen, Wissen, Daten, Analysen" (LWDA)}}, pages = {271--283}, location = {Rostock, Germany}, month = {September 11--13}, series = {{CEUR} Workshop Proceedings}, volume = {1917}, publisher = {CEUR-WS.org}, year = {2017} }