Ballesteros, MiguelCarreras, Xavier2016-12-192016-12-192015Ballesteros M, Carreras X. Transition-based spinal parsing. In: Proceedings of the 19th Conference on Computational Language Learning (CoNLL 2015). 2015 July 30-31; Beijing, China. [Stroudsburg]: ACL, 2015. p.289-99.http://hdl.handle.net/10230/27787Comunicació presentada a la 19th Conference on Computational Language Learning, celebrada els dies 30 i 31 de juliol 2015 a Beijing (China) i organitzada per l'ACL Special Interest Group on Natural Language Learning.We present a transition-based arc-eager model to parse spinal trees, a dependencybased representation that includes phrasestructure information in the form of constituent spines assigned to tokens. As a main advantage, the arc-eager model can use a rich set of features combining dependency and constituent information, while parsing in linear time. We describe a set of conditions for the arc-eager system to produce valid spinal structures. In experiments using beam search we show that the model obtains a good trade-off between speed and accuracy, and yields state of the art performance for both dependency and constituent parsing measures.application/pdfeng© ACL, Creative Commons Attribution-NonCommercial-ShareAlike 3.0 International LicenseTractament del llenguatge natural (Informàtica)Lingüística computacionalinfo:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/openAccess