Enriching a Valency Lexicon by Deverbative Nouns

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F16%3A10335461" target="_blank" >RIV/00216208:11320/16:10335461 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Enriching a Valency Lexicon by Deverbative Nouns

Popis výsledku v původním jazyce

In this paper, we present an attempt to automatically identify Czech deverbative nouns using several methods that use large corpora as well as existing lexical resources. The motivation for the task is to extend a verbal valency (i.e., predicate-argument) lexicon by adding nouns that share the valency properties with the base verb, assuming their properties can be derived (even if not trivially) from the underlying verb by deterministic grammatical rules. At the same time, even in inflective languages, not all deverbatives are simply created from their underlying base verb by regular lexical derivation processes. We have thus developed hybrid techniques that use both large parallel corpora and several standard lexical resources. Thanks to the use of parallel corpora, the resulting sets contain also synonyms, which the lexical derivation rules cannot get. For evaluation, we have manually created a gold dataset of deverbative nouns linked to 100 frequent Czech verbs since no such dataset was initially a

Název v anglickém jazyce

Enriching a Valency Lexicon by Deverbative Nouns

Popis výsledku anglicky

In this paper, we present an attempt to automatically identify Czech deverbative nouns using several methods that use large corpora as well as existing lexical resources. The motivation for the task is to extend a verbal valency (i.e., predicate-argument) lexicon by adding nouns that share the valency properties with the base verb, assuming their properties can be derived (even if not trivially) from the underlying verb by deterministic grammatical rules. At the same time, even in inflective languages, not all deverbatives are simply created from their underlying base verb by regular lexical derivation processes. We have thus developed hybrid techniques that use both large parallel corpora and several standard lexical resources. Thanks to the use of parallel corpora, the resulting sets contain also synonyms, which the lexical derivation rules cannot get. For evaluation, we have manually created a gold dataset of deverbative nouns linked to 100 frequent Czech verbs since no such dataset was initially a

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

<a href="/cs/project/DG16P02B048" target="_blank" >DG16P02B048: Systém pro trvalé uchování dokumentace a prezentaci historických pramenů z období totalitních režimů</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2016

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the Workshop on Grammar and Lexicon: Interactions and Interfaces (GramLex)

ISBN

978-4-87974-706-8

ISSN

—

e-ISSN

—

Počet stran výsledku

10

Strana od-do

71-80

Název nakladatele

The COLING 2016 Organizing Committee

Místo vydání

Ōsaka, Japan

Místo konání akce

Osaka, Japan

Datum konání akce

11. 12. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—