Show simple item record

dc.rights.licenseCC-BY-NC-ND
dc.contributor.advisorFowlie, M.
dc.contributor.advisorWegmann, A.M.
dc.contributor.authorMaatman, P.Q.
dc.date.accessioned2021-03-02T19:00:17Z
dc.date.available2021-03-02T19:00:17Z
dc.date.issued2020
dc.identifier.urihttps://studenttheses.uu.nl/handle/20.500.12932/39031
dc.description.abstractThis study investigates the effect of incrementality on the accuracy of parsers on garden path sentences. We show that the incremental parser evaluated in this thesis achieves lower accuracies on garden path sentences than a nonincremental parser. We then explore one explanation for this worse accuracy of the incremental parser and we find two likely sources for error: either the scoring function, or the transition system is the culprit. We suggest further research to investigate which of of the two sources of error contribute the most.
dc.description.sponsorshipUtrecht University
dc.format.extent319809
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.titleTo be incremental or not: PreTra and RBGParser evaluated on garden path sentences
dc.type.contentBachelor Thesis
dc.rights.accessrightsOpen Access
dc.subject.keywordsincremental parsing, garden path sentences, pretra, rbgparser, parsing, nlp
dc.subject.courseuuKunstmatige Intelligentie


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record