Normal view MARC view ISBD view

Cross-Lingual Dependency Parsing of Related Languages with Rich Morphosyntactic Tagsets / Agić, Željko ; Tiedemann, Jörg ; Dobrovoljc, Kaja ; Krek, Simon ; Merkler, Danijela ; Može, Sara.

By: Agić, Željko.
Contributor(s): Tiedemann, Jörg [aut] | Dobrovoljc, Kaja [aut] | Krek, Simon Merkler, Danijela [aut] | Može, Sara [aut].
Material type: ArticleArticleDescription: 12-23 str.Other title: Cross-Lingual Dependency Parsing of Related Languages with Rich Morphosyntactic Tagsets [Naslov na engleskom:].Subject(s): 5.04 | cross-lingual parsing, dependency parsing, machine translation hrv | cross-lingual parsing, dependency parsing, machine translation engOnline resources: Click here to access online | Click here to access online In: EMNLP 2014 Workshop on Language Technology for Closely Related Languages and Language Variants (25-29.10.2014. ; Doha, Katar) Proceedings of the EMNLP 2014 Workshop on Language Technology for Closely Related Languages and Language Variants str. 12-23Summary: 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 cross-lingual 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.
Tags from this library: No tags from this library for this title. Log in to add tags.
No physical items for this record

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 cross-lingual 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.

Projekt MZOS 130-1300646-1776

ENG

There are no comments for this item.

Log in to your account to post a comment.

Powered by Koha

//