Three Syntactic Formalisms for Data-Driven Dependency Parsing of Croatian
A new syntactic formalism for dependency parsing of Croatian and its implementation in the SETimes Dependency Treebank of Croatian – the Setimes.Hr Treebank – is presented. Its new syntactic tagset is targeted towards improving dependency parsing accuracy, with special emphasis on the main syntactic...
| Permalink: | http://skupni.nsk.hr/Record/ffzg.KOHA-OAI-FFZG:313337/Details |
|---|---|
| Matična publikacija: |
Text, Speech and Dialogue : 16th International Conference, TSD 2013, Pilsen, Czech Republic, September 1-5, 2013. : Proceedings Lecture Notes in Computer Science |
| Glavni autori: | Agić, Željko (-), Merkler, Danijela (Author) |
| Vrsta građe: | Članak |
| Jezik: | eng |
| Online pristup: |
http://link.springer.com/chapter/10.1007/978-3-642-40585-3_70 |
| LEADER | 02270naa a2200253uu 4500 | ||
|---|---|---|---|
| 008 | 131111s2013 xx eng|d | ||
| 020 | |a 9783-642-40584-6 | ||
| 035 | |a (CROSBI)639141 | ||
| 040 | |a HR-ZaFF |b hrv |c HR-ZaFF |e ppiak | ||
| 100 | 1 | |9 495 |a Agić, Željko | |
| 245 | 1 | 0 | |a Three Syntactic Formalisms for Data-Driven Dependency Parsing of Croatian / |c Agić, Željko ; Merkler, Danijela. |
| 246 | 3 | |i Naslov na engleskom: |a Three Syntactic Formalisms for Data-Driven Dependency Parsing of Croatian | |
| 300 | |a 560-567 |f str. | ||
| 520 | |a A new syntactic formalism for dependency parsing of Croatian and its implementation in the SETimes Dependency Treebank of Croatian – the Setimes.Hr Treebank – is presented. Its new syntactic tagset is targeted towards improving dependency parsing accuracy, with special emphasis on the main syntactic categories such as predicates, subjects and objects. It is compared with two versions of Croatian Dependency Treebank (HOBS): one with explicit encoding of subordinate syntactic conjunctions and one without. Manual annotation quality and dependency parsing accuracy were inspected. An improvement in inter-annotator agreement was observed, as Cohen’s kappa coefficient for label attachment κ(LA) peaked at 0.92, topping the two HOBS instances by 0.036 and 0.081 points. Overall dependency parsing accuracy reached 77.49 in labeled attachment (LAS), 2.99 and 5.78 points over HOBS, using a standard graph-based dependency parser. | ||
| 536 | |a Projekt MZOS |f 130-1300646-1776 | ||
| 546 | |a ENG | ||
| 690 | |a 5.04 | ||
| 693 | |a dependency treebank, dependency parsing, Croatian language |l hrv |2 crosbi | ||
| 693 | |a dependency treebank, dependency parsing, Croatian language |l eng |2 crosbi | ||
| 773 | 0 | |t Text, Speech and Dialogue : 16th International Conference, TSD 2013, Pilsen, Czech Republic, September 1-5, 2013. : Proceedings |d Berlin, Heidelberg : Springer, 2013 |k Lecture Notes in Computer Science |h 601 |n Habernal, Ivan ; Matoušek, Václav |z 978-3-642-40584-6 |g str. 560-567 |a International Conference, TSD 2013 (16 ; 2013 ; Pilsen, Czech Republic) | |
| 700 | 1 | |9 868 |a Merkler, Danijela |4 aut | |
| 856 | |u http://link.springer.com/chapter/10.1007/978-3-642-40585-3_70 | ||
| 942 | |c RZB |t 1.08 |u 2 |z Znanstveni | ||
| 999 | |c 313337 |d 313335 | ||