This paper introduces TakeFive, a new semantic role labeling method that transforms a text into a frame-oriented knowledge graph. It performs dependency parsing, identifies the words that evoke lexical frames, locates the roles and fillers for each frame, runs coercion techniques, and formalizes the results as a knowledge graph. This formal representation complies with the frame semantics used in Framester, a factual-linguistic linked data resource. We tested our method on the WSJ section of the Peen Treebank annotated with VerbNet and PropBank labels and on the Brown corpus. The evaluation has been performed according to the CoNLL Shared Task on Joint Parsing of Syntactic and Semantic Dependencies. The obtained precision, recall, and F1 values indicate that TakeFive is competitive with other existing methods such as SEMAFOR, Pikes, PathLSTM, and FRED. We finally discuss how to combine TakeFive and FRED, obtaining higher values of precision, recall, and F1 measure.

Semantic role labeling for knowledge graph extraction from text / Alam M.; Gangemi A.; Presutti V.; Reforgiato Recupero D.. - In: PROGRESS IN ARTIFICIAL INTELLIGENCE. - ISSN 2192-6352. - ELETTRONICO. - 10:3(2021), pp. 309-320. [10.1007/s13748-021-00241-7]

Semantic role labeling for knowledge graph extraction from text

Gangemi A.
;
Presutti V.
;
2021

Abstract

This paper introduces TakeFive, a new semantic role labeling method that transforms a text into a frame-oriented knowledge graph. It performs dependency parsing, identifies the words that evoke lexical frames, locates the roles and fillers for each frame, runs coercion techniques, and formalizes the results as a knowledge graph. This formal representation complies with the frame semantics used in Framester, a factual-linguistic linked data resource. We tested our method on the WSJ section of the Peen Treebank annotated with VerbNet and PropBank labels and on the Brown corpus. The evaluation has been performed according to the CoNLL Shared Task on Joint Parsing of Syntactic and Semantic Dependencies. The obtained precision, recall, and F1 values indicate that TakeFive is competitive with other existing methods such as SEMAFOR, Pikes, PathLSTM, and FRED. We finally discuss how to combine TakeFive and FRED, obtaining higher values of precision, recall, and F1 measure.
2021
Semantic role labeling for knowledge graph extraction from text / Alam M.; Gangemi A.; Presutti V.; Reforgiato Recupero D.. - In: PROGRESS IN ARTIFICIAL INTELLIGENCE. - ISSN 2192-6352. - ELETTRONICO. - 10:3(2021), pp. 309-320. [10.1007/s13748-021-00241-7]
Alam M.; Gangemi A.; Presutti V.; Reforgiato Recupero D.
File in questo prodotto:
File Dimensione Formato  
s13748-021-00241-7-1.pdf

accesso aperto

Tipo: Versione (PDF) editoriale
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione 761.98 kB
Formato Adobe PDF
761.98 kB Adobe PDF Visualizza/Apri

I documenti in IRIS 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/11585/899027
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 9
  • ???jsp.display-item.citation.isi??? 2
social impact