
Anders Björkelund
Forskare

IMS at the CoNLL 2017 UD Shared Task: CRFs and Perceptrons Meet Neural Networks
Författare
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.
Publiceringsår
2017-08-01
Språk
Engelska
Sidor
40-51
Publikation/Tidskrift/Serie
Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
Länkar
Dokumenttyp
Konferensbidrag
Förlag
Association for Computational Linguistics
Ämne
- Language Technology (Computational Linguistics)
Aktiv
Published