Linguistically-driven Selection of Correct Arcs for Dependency Parsing
Fuente:
Redalyc
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Artículo científico |
| Sprache: | en |
| Veröffentlicht: |
Instituto Politécnico Nacional
2013
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1876475859448102912 |
|---|---|
| author | Felice Dell’Orletta |
| author_facet | Felice Dell’Orletta |
| contents | Linguistically-driven Selection of Correct Arcs for Dependency Parsing Felice Dell’Orletta Giulia Venturi Simonetta Montemagni Computación correct arcs arcos correctos Dependency parsing Análisis sintáctico de dependencias LISCA is an unsupervised algorithm aimed at assigning a quality score to each arc generated by a dependency parser in order to produce a decreasing ranking of arcs from correct to incorrect ones. LISCA exploits statistics about a set of linguistically-motivated and dependency-based features extracted from a large corpus of automatically parsed sentences and uses them to assign a quality score to each arc of a parsed sentence belonging to the same domain of the automatically parsed corpus. LISCA has been successfully tested on two datasets belonging to two different domains and in all experiments it turned out to outperform different baselines, thus showing to be able to reliably detect correct arcs also representing domain-specific peculiarities. 2013 artículo científico 1405-5546 https://www.redalyc.org/articulo.oa?id=61527437003 en http://www.redalyc.org/revista.oa?id=615 Computación y Sistemas application/pdf Instituto Politécnico Nacional Computación y Sistemas (México) Num.2 Vol.17 |
| format | Artículo científico |
| id | redalyc_61527437003 |
| institution | Redalyc |
| language | en |
| publishDate | 2013 |
| publisher | Instituto Politécnico Nacional |
| spellingShingle | Linguistically-driven Selection of Correct Arcs for Dependency Parsing Felice Dell’Orletta Computación correct arcs arcos correctos Dependency parsing Análisis sintáctico de dependencias Linguistically-driven Selection of Correct Arcs for Dependency Parsing Felice Dell’Orletta Giulia Venturi Simonetta Montemagni Computación correct arcs arcos correctos Dependency parsing Análisis sintáctico de dependencias LISCA is an unsupervised algorithm aimed at assigning a quality score to each arc generated by a dependency parser in order to produce a decreasing ranking of arcs from correct to incorrect ones. LISCA exploits statistics about a set of linguistically-motivated and dependency-based features extracted from a large corpus of automatically parsed sentences and uses them to assign a quality score to each arc of a parsed sentence belonging to the same domain of the automatically parsed corpus. LISCA has been successfully tested on two datasets belonging to two different domains and in all experiments it turned out to outperform different baselines, thus showing to be able to reliably detect correct arcs also representing domain-specific peculiarities. 2013 artículo científico 1405-5546 https://www.redalyc.org/articulo.oa?id=61527437003 en http://www.redalyc.org/revista.oa?id=615 Computación y Sistemas application/pdf Instituto Politécnico Nacional Computación y Sistemas (México) Num.2 Vol.17 |
| title | Linguistically-driven Selection of Correct Arcs for Dependency Parsing |
| topic | Computación correct arcs arcos correctos Dependency parsing Análisis sintáctico de dependencias |
| url | https://www.redalyc.org/articulo.oa?id=61527437003 |