In this paper we will develop the argument indirectly raised by the organizer of 2014 Dependency Parsing for Information Extraction task when they classify 19 relations out of 45 as those semantically relevant for the evaluation, and exclude the others which confirms our stance which considers the new paradigm of Dependency parsing evaluation favoured in comparison to the previous parsing scheme based mainly on constituent or phrase structure evaluation. We will also speak in favour of rule-based dependency parsing and against statistically based dependency parsers for reasons related to the role played by the SUBJect relation in Italian.

A Reevaluation of Dependency Structure Evaluation

DELMONTE, Rodolfo
2014-01-01

Abstract

In this paper we will develop the argument indirectly raised by the organizer of 2014 Dependency Parsing for Information Extraction task when they classify 19 relations out of 45 as those semantically relevant for the evaluation, and exclude the others which confirms our stance which considers the new paradigm of Dependency parsing evaluation favoured in comparison to the previous parsing scheme based mainly on constituent or phrase structure evaluation. We will also speak in favour of rule-based dependency parsing and against statistically based dependency parsers for reasons related to the role played by the SUBJect relation in Italian.
2014
Proceedings of CLiC-it 2014 - The First Italian Conference on Computational Linguistics
File in questo prodotto:
File Dimensione Formato  
AReevaluation2.pdf

accesso aperto

Tipologia: Documento in Post-print
Licenza: Accesso libero (no vincoli)
Dimensione 219.3 kB
Formato Adobe PDF
219.3 kB Adobe PDF Visualizza/Apri

I documenti in ARCA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10278/43536
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact