Za projektivitou: mnohojazyčné vyhodnocení omezení a měr na neprojektivních strukturách

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F07%3A00101507" target="_blank" >RIV/00216208:11320/07:00101507 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Beyond Projectivity: Multilingual Evaluation of Constraints and Measures on Non-Projective Structures

Popis výsledku v původním jazyce

Dependency analysis of natural language has gained importance for its applicability in tasks of NLP. Non-projective structures are common in dependency analysis, therefore we need fine-grained means of describing them, especially for the purposes of machine-learning oriented approaches like parsing. We present an evaluation on twelve languages which explores several constraints and measures on non-projective structures. We pursue an edge-based approach concentrating on properties of individual edges asopposed to properties of whole trees. In our evaluation, we include previously unreported measures taking into account levels of nodes in dependency trees. Our empirical results corroborate theoretical results and show that an edge-based approach using levels of nodes provides an accurate and at the same time expressive means for capturing non-projective structures in natural language.

Název v anglickém jazyce

Beyond Projectivity: Multilingual Evaluation of Constraints and Measures on Non-Projective Structures

Popis výsledku anglicky

Dependency analysis of natural language has gained importance for its applicability in tasks of NLP. Non-projective structures are common in dependency analysis, therefore we need fine-grained means of describing them, especially for the purposes of machine-learning oriented approaches like parsing. We present an evaluation on twelve languages which explores several constraints and measures on non-projective structures. We pursue an edge-based approach concentrating on properties of individual edges asopposed to properties of whole trees. In our evaluation, we include previously unreported measures taking into account levels of nodes in dependency trees. Our empirical results corroborate theoretical results and show that an edge-based approach using levels of nodes provides an accurate and at the same time expressive means for capturing non-projective structures in natural language.

Druh

D - Stať ve sborníku

CEP obor

AI - Jazykověda

OECD FORD obor

—

Projekt

<a href="/cs/project/1ET201120505" target="_blank" >1ET201120505: Od jazyka ke znalostem a sémantickému webu</a><br>

Návaznosti

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

Rok uplatnění

2007

Kód důvěrnosti údajů

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

Název statě ve sborníku

ACL 2008 Proceedings of the 46th Annual Meeting of the Association of Computational Linguistics: Human Language Technologies

ISBN

978-1-932432-06-0

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

—

Název nakladatele

Association for Computational Linguistics

Místo vydání

—

Místo konání akce

Neuveden

Datum konání akce

1. 1. 2007

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—