Normal view MARC view ISBD view

Verb Valency Frame Extraction Using Morphological and Syntactic Features of Croatian / Šojat, Krešimir ; Agić, Željko ; Tadić, Marko.

By: Šojat, Krešimir.
Contributor(s): Tadić, Marko [aut] | Agić, Željko [aut].
Material type: materialTypeLabelArticleDescription: 119-126.Other title: Verb Valency Frame Extraction Using Morphological and Syntactic Features of Croatian [Naslov na engleskom:].Subject(s): 5.04 | 6.03 | verb valency, valency lexicon, valency frame extraction, Croatian dependency treebank hrv | verb valency, valency lexicon, valency frame extraction, Croatian dependency treebank engOnline resources: Click here to access online In: Formal Approaches on South Slavic and Balkan Languages (04-06.10.2010. ; Dubrovnik, Hrvatska) Proceedings of the 7th International Conference on Formal Approaches to South Slavic and Balkan Languages str. 119-126Tadić, Marko ; Dimitrova-Vulchanova, Mila ; Koeva, SvetlaSummary: The paper presents an approach to valency frame extraction for Croatian verbs on basis of morphological and syntactic features of wordforms from syntactically annotated sentences. We have used a gold standard sample of approximately 1200 sentences and 30.000 tokens from the Croatian Dependency Treebank and a frame instance extraction algorithm. We extracted 936 verb frame instances for 424 different verbs – consisting of lemmas, morphosyntactic tags and syntactic functions of the encountered wordforms – and manually assigned tectogrammatical functors to their elements. Distributional properties are given in terms of co-occurrences for each of these features. The obtained results will serve for further development of valency frame extraction procedures.
Tags from this library: No tags from this library for this title. Log in to add tags.
No physical items for this record

The paper presents an approach to valency frame extraction for Croatian verbs on basis of morphological and syntactic features of wordforms from syntactically annotated sentences. We have used a gold standard sample of approximately 1200 sentences and 30.000 tokens from the Croatian Dependency Treebank and a frame instance extraction algorithm. We extracted 936 verb frame instances for 424 different verbs – consisting of lemmas, morphosyntactic tags and syntactic functions of the encountered wordforms – and manually assigned tectogrammatical functors to their elements. Distributional properties are given in terms of co-occurrences for each of these features. The obtained results will serve for further development of valency frame extraction procedures.

Projekt MZOS 130-1300646-0645

Projekt MZOS 130-1300646-1002

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