Real Anaphora Resolution Is Hard

The Case of German
  • Manfred Klenner
  • Angela Fahrni
  • Rico Sennrich
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6231)


We introduce a system for anaphora resolution for German that uses various resources in order to develop a real system as opposed to systems based on idealized assumptions, e.g. the use of true mentions only or perfect parse trees and perfect morphology. The components that we use to replace such idealizations comprise a full-fledged morphology, a Wikipedia-based named entity recognition, a rule-based dependency parser and a German wordnet. We show that under these conditions coreference resolution is (at least for German) still far from being perfect.


Noun Phrase Personal Pronoun Computational Linguistics Syntactic Information Grammatical Function 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Klenner, M., Ailloud, E.: Optimization in Coreference Resolution Is Not Needed: A Nearly-Optimal Zero-One ILP Algorithm with Intensional Constraints. In: Proceedings of the EACL (2009)Google Scholar
  2. 2.
    Hamp, B., Feldweg, H.: GermaNet—a Lexical-Semantic Net for German. In: Proc. of ACL Workshop Automatic Information Extraction and Building of Lexical Semantic Resources for NLP Applications (1997)Google Scholar
  3. 3.
    Daelemans, W., Zavrel, J., van der Sloot, K., van den Bosch, A.: TiMBL: Tilburg Memory-Based Learner (2004)Google Scholar
  4. 4.
    Schneider, G.: Hybrid Long-Distance Functional Dependency Parsing. Doctoral Thesis, Institute of Computational Linguistics, Univ. of Zurich (2008)Google Scholar
  5. 5.
    Telljohann, H., Hinrichs, E.W., Kübler, S.: The TüBa-D/Z Treebank: Annotating German with a Context-Free Backbone. In: Proc. of the Fourth Intern. Conf. on Language Resources and Evaluation, Lisbon, Portugal (2004)Google Scholar
  6. 6.
    Sennrich, R., Schneider, G., Volk, M., Warin, M.: A New Hybrid Dependency Parser for German. In: Proc. of the German Society for Computational Linguistics and Language Technology 2009 (GSCL 2009), Potsdam, Germany, pp. 115–124 (2009)Google Scholar
  7. 7.
    Naumann, K.: Manual for the Annotation of Indocument Referential Relations. Electronic document, (2006),
  8. 8.
    Soon, W., Ng, H., Lim, D.: A Machine Learning Approach to Coreference Resolution of Noun Phrases. Computational Linguistics 27(4), 521–544 (2001)CrossRefGoogle Scholar
  9. 9.
    Versley, Y.: A Constraint-Based Approach to Noun Phrase Coreference Resolution in German Newspaper Text. In: Konferenz zur Verarbeitung Natürlicher Sprache, KONVENS (2006)Google Scholar
  10. 10.
    Hinrichs, E., Filippova, K., Wunsch, H.: A Data-driven Approach to Pronominal Anaphora Resolution in German. In: Proc. of RANLP (2005)Google Scholar
  11. 11.
    Wunsch, H., Kübler, S., Cantrell, R.: Instance Sampling Methods for Pronoun Resolution. In: Proc. of RANLP, Borovets, Bulgaria (2009)Google Scholar
  12. 12.
    Schiehlen, M.: Optimizing Algorithms for Pronoun Resolution. In: Proceed. of the 20th International Conference on Computational Linguistics (2004)Google Scholar
  13. 13.
    Klenner, M., Ailloud, E.: Enhancing Coreference Clustering. In: Johansson, C. (ed.) Proc. of the Second Workshop on Anaphora Resolution (WAR II), Bergen, Norway. NEALT Proceedings Series, vol. 2 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Manfred Klenner
    • 1
  • Angela Fahrni
    • 1
  • Rico Sennrich
    • 1
  1. 1.Institute of Computational LinguisticsZurich

Personalised recommendations