Loading...
Cross-lingual Dependency Parsing of Related Languages with Rich Morphosyntactic Tagsets
Agić, Željko Tiedemann, Jörg Merkler, Danijela Krek, Simon Dobrovoljc, Kaja Moze, Sara
Agić, Željko
Tiedemann, Jörg
Merkler, Danijela
Krek, Simon
Dobrovoljc, Kaja
Moze, Sara
Editors
Other contributors
Affiliation
Epub Date
Issue Date
2014
Submitted date
Subjects
Alternative
Abstract
This paper addresses cross-lingual dependency parsing using rich morphosyntactic tagsets. In our case study, we experiment with three related Slavic languages:
Croatian, Serbian and Slovene. Four different dependency treebanks are used for
monolingual parsing, direct cross-lingual
parsing, and a recently introduced crosslingual parsing approach that utilizes statistical machine translation and annotation projection. We argue for the benefits
of using rich morphosyntactic tagsets in
cross-lingual parsing and empirically support the claim by showing large improvements over an impoverished common feature representation in form of a reduced
part-of-speech tagset. In the process, we
improve over the previous state-of-the-art
scores in dependency parsing for all three
languages.
Citation
Language Technology for Closely Related Languages and Language Variants (LT4CloseLang), pages 13–24, October 29, 2014, Doha, Qatar
Research Unit
PubMed ID
PubMed Central ID
Embedded videos
Additional Links
Type
Conference contribution
Language
en
Description
Series/Report no.
ISSN
EISSN
ISBN
9781937284961