How difficult is the adaptation of POS taggers?

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

Domain adaptation is a difficult problem, but also a relevant one. Unsupervised domain adaptation focuses on adapting a model from a source domain, which includes plenty of labeled data, to a target domain that provides no labeled data. This is the most compelling setting of domain adaptation, but it is also the most difficult one. We perform an experimental analysis to highlight how difficult this problem is. We show that the best available unsupervised domain adaptation system for POS tagging can be outperformed by a simple POS tagger that has access to only 250 labeled sentences from the target domain. This is not a fair comparison between these two systems, of course; but it highlights that unsupervised domain adaptation is not well solved yet. Moreover, the best available systems are not yet practical, since they are complex, difficult to implement, and do not achieve significant improvements.

Original languageEnglish
Title of host publicationBRACIS 2017 : 2017 Brazilian Conference on Intelligent Systems : Uberlândia, MG, Brazil, 2-5 October 2017 : proceedings
Number of pages6
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers Inc.
Publication date28.06.2017
Pages360-365
ISBN (print)978-1-5386-2408-1
ISBN (electronic)978-1-5386-2407-4
DOIs
Publication statusPublished - 28.06.2017
Externally publishedYes
EventBrazilian Conference on Intelligent Systems - BRACIS 2017 - Uberlandia, Brazil
Duration: 02.10.201705.10.2017
Conference number: 6

DOI

Recently viewed

Publications

  1. Introduction
  2. Contrasting patterns of intraspecific trait variability in native and non-native plant species along an elevational gradient on Tenerife, Canary Islands
  3. Landscape modification and habitat fragmentation: a synthesis
  4. Halb voll oder halb leer?
  5. Understanding Environmental Posts
  6. Analysis of Dynamic Response of a Two Degrees of Freedom (2-DOF) Ball Bearing Nonlinear Model
  7. The use of the online Inverted Classroom Model for digital teaching with gamification in medical studies
  8. Mit "gesunder" Mischung zu Stabilität und Integration?
  9. Aligning the design of intermediary organisations with the ecosystem
  10. Two-way NxP fertilisation experiment on barley (Hordeum vulgare) reveals shift from additive to synergistic N-P interactions at critical phosphorus fertilisation level
  11. Digital transformation in an incumbent organisation
  12. Automated system for measuring the radial clearance of rolling bearings
  13. Pragmatic Function of Twitter Handlers' Perspectives on Children Discourse in Nigeria.
  14. Development of a magnesium recycling alloy based on the AM alloy system
  15. A leverage points perspective on social networks to understand sustainability transformations
  16. Körperlernen
  17. Nanoindentation of Poly(Ethylene Oxide) Nanofibers by Atomic Force Microscope (AFM)
  18. The predictive value of individual and work-related resources for the health and work satisfaction of German school principals
  19. Introduction: Modeling the Pacific Ocean
  20. Nonprofit-Organizations and Society
  21. Concept of a cloud state modeling system for lead-acid batteries
  22. Nonlinear recurrence analysis of piezo sensor placement for unmanned aerial vehicle motor failure diagnosis
  23. Impacts of entrepreneur’s error orientation on performance: A cross-culture comparison
  24. A panel cointegration rank test with structural breaks and cross-sectional dependence
  25. Porträt ohne Modell
  26. Leading digital innovation in schools
  27. Gemeinsam glücklicher
  28. Non-linear effects of comparison income in quit decisions: status versus signal !