Your browser has javascript turned off or blocked. This will lead to some parts of our website to not work properly or at all. Turn on javascript for best performance.

The browser you are using is not supported by this website. All versions of Internet Explorer are no longer supported, either by us or Microsoft (read more here: https://www.microsoft.com/en-us/microsoft-365/windows/end-of-ie-support).

Please use a modern browser to fully experience our website, such as the newest versions of Edge, Chrome, Firefox or Safari etc.

Physics lego figure. Photo.

Anders Björkelund

Postdoc

Physics lego figure. Photo.

IMS at the CoNLL 2017 UD Shared Task: CRFs and Perceptrons Meet Neural Networks

Author

  • Anders Björkelund
  • Agnieszka Falenska
  • Xiang Yu
  • Jonas Kuhn

Summary, in English

This paper presents the IMS contribution to the CoNLL 2017 Shared Task. In the preprocessing step we employed a CRF POS/morphological tagger and a neural tagger predicting supertags. On some languages, we also applied word segmentation with the CRF tagger and sentence segmentation with a perceptron-based parser. For parsing we took an ensemble approach by blending multiple instances of three parsers with very different architectures. Our system achieved the third place overall and the second place for the surprise languages.

Publishing year

2017-08-01

Language

English

Pages

40-51

Publication/Series

Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

Document type

Conference paper

Publisher

Association for Computational Linguistics

Topic

  • Language Technology (Computational Linguistics)

Status

Published