Cross-Lingual Dependency Parsing of Related Languages with Rich Morphosyntactic Tagsets
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 rec...
| Permalink: | http://skupnikatalog.nsk.hr/Record/ffzg.KOHA-OAI-FFZG:335558/Details |
|---|---|
| Matična publikacija: |
Proceedings of the EMNLP 2014 Workshop on Language Technology for Closely Related Languages and Language Variants Doha, Qatar : Association for Computational Linguistics, 2014 |
| Glavni autori: | Agić, Željko (-), Tiedemann, Jörg (Author), Dobrovoljc, Kaja, Krek, Simon Merkler, Danijela, Može, Sara |
| Vrsta građe: | Članak |
| Jezik: | eng |
| Online pristup: |
http://bib.irb.hr/datoteka/716682.agic2014-cross.pdf http://www.aclweb.org/anthology/W14/W14-4202 |
| LEADER | 02406naa a22003017i 4500 | ||
|---|---|---|---|
| 005 | 20170115202523.0 | ||
| 008 | 150109s2014 qa 1 eng|d | ||
| 035 | |a (CROSBI)716682 | ||
| 040 | |a HR-ZaFF |b hrv |c HR-ZaFF |e ppiak | ||
| 100 | 1 | |9 495 |a Agić, Željko | |
| 245 | 1 | 0 | |a Cross-Lingual Dependency Parsing of Related Languages with Rich Morphosyntactic Tagsets / |c Agić, Željko ; Tiedemann, Jörg ; Dobrovoljc, Kaja ; Krek, Simon ; Merkler, Danijela ; Može, Sara. |
| 246 | 3 | |i Naslov na engleskom: |a Cross-Lingual Dependency Parsing of Related Languages with Rich Morphosyntactic Tagsets | |
| 300 | |a 12-23 |f str. | ||
| 520 | |a 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. | ||
| 536 | |a Projekt MZOS |f 130-1300646-1776 | ||
| 546 | |a ENG | ||
| 690 | |a 5.04 | ||
| 693 | |a cross-lingual parsing, dependency parsing, machine translation |l hrv |2 crosbi | ||
| 693 | |a cross-lingual parsing, dependency parsing, machine translation |l eng |2 crosbi | ||
| 700 | 1 | |a Tiedemann, Jörg |4 aut | |
| 700 | 1 | |a Dobrovoljc, Kaja |4 aut | |
| 700 | 1 | |a Krek, Simon |4 aut |a Merkler, Danijela | |
| 700 | 1 | |a Može, Sara |4 aut | |
| 773 | 0 | |a EMNLP 2014 Workshop on Language Technology for Closely Related Languages and Language Variants (25-29.10.2014. ; Doha, Katar) |t Proceedings of the EMNLP 2014 Workshop on Language Technology for Closely Related Languages and Language Variants |d Doha, Qatar : Association for Computational Linguistics, 2014 |z 978-1-937284-96-1 |g str. 12-23 | |
| 856 | |u http://bib.irb.hr/datoteka/716682.agic2014-cross.pdf | ||
| 856 | |u http://www.aclweb.org/anthology/W14/W14-4202 | ||
| 942 | |c RZB |u 2 |v Recenzija |z Znanstveni - Predavanje - CijeliRad |t 1.08 | ||
| 999 | |c 335558 |d 335555 | ||