Latent structure perceptron with feature induction for unrestricted coreference resolution

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

Authors

We describe a machine learning system based on large margin structure perceptron for unrestricted coreference resolution that introduces two key modeling techniques: latent coreference trees and entropy guided feature induction. The proposed latent tree modeling turns the learning problem computationally feasible. Additionally, using an automatic feature induction method, we are able to efficiently build nonlinear models and, hence, achieve high performances with a linear learning algorithm. Our system is evaluated on the CoNLL-2012 Shared Task closed track, which comprises three languages: Arabic, Chinese and English. We apply the same system to all languages, except for minor adaptations on some language dependent features, like static lists of pronouns. Our system achieves an official score of 58.69, the best one among all the competitors.

Original languageEnglish
Title of host publicationJoint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning : EMNLP-CoNLL 2012; Proceedings of the Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes, July 13, 2012
Number of pages8
Place of PublicationStroudsburg
PublisherAssociation for Computational Linguistics (ACL)
Publication date2012
Pages41-48
ISBN (electronic)978-1-937284-45-9
Publication statusPublished - 2012
Externally publishedYes
Event2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning - EMNLP-CoNLL 2012: Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes - Jeju Island, Korea, Republic of
Duration: 12.07.201214.07.2012

Recently viewed

Publications

  1. Dispatching rule selection with Gaussian processes
  2. A computational study of a model of single-crystal strain-gradient viscoplasticity with an interactive hardening relation
  3. Using CNNs to Detect Graphical Representations of Structural Equation Models in IS Papers
  4. A sensor fault detection scheme as a functional safety feature for DC-DC converters
  5. Simulation based optimization of lot sizes for opposing logistic objectives
  6. Distinguishing state variability from trait change in longitudinal data
  7. A PD regulator to minimize noise effect using a minimal variance method for soft landing control of an electromagnetic valve actuator
  8. Mapping the intersection of planetary boundaries and environmentally extended input-output analysis: A systematic literature review
  9. Biodiversity-multifunctionality relationships depend on identity and number of measured functions
  10. Methodological support for the selection of simplified equations of state for modeling technical fluids
  11. A data-driven methodological routine to identify key indicators for social-ecological system archetype mapping
  12. Integrating Common Ground and Informativeness in Pragmatic Word Learning
  13. Modelling biodegradability based on OECD 301D data for the design of mineralising ionic liquids
  14. Multi-agent systems' asset for smart grid applications
  15. Finite element based determination and optimization of seam weld positions in porthole die extrusion of double hollow profile with asymmetric cross section
  16. Surveying the FAIRness of Annotation Tools: Difficult to find, difficult to reuse
  17. "The skin and fur on your shoulders"
  18. The EU at a crossroads. Negotiations about the multiannual financial framework 2021-2027
  19. Personality traits moderate the relationships between psychological needs and enjoyment of physical activity
  20. Microstructural investigations of the Mg-Sn and Mg-Sn-Al alloy systems
  21. Digital Religious Communication and the Facilitation of Social Resilience
  22. Blended learning