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

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceeding

Abstract

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.

Details

Authors
External organisations
  • University of Stuttgart
Research areas and keywords

Subject classification (UKÄ) – MANDATORY

  • Language Technology (Computational Linguistics)
Original languageEnglish
Title of host publicationProceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
Place of PublicationVancouver, Canada
PublisherAssociation for Computational Linguistics
Pages40-51
Number of pages12
Publication statusPublished - 2017 Aug 1
Publication categoryResearch
Peer-reviewedYes
Externally publishedYes