Frame semantics is a well-established framework to represent the meaning of natural language in computational terms. In this work, we aim to propose a quantitative measure of relatedness between pairs of frame instances. We test our method on a dataset of sentence pairs, highlighting the correlation between our metric and human judgments of semantic similarity. Furthermore, we propose an application of our measure for clustering frame instances to extract prototypical knowledge from natural language.

Measuring Frame Instance Relatedness

Valerio Basile;
2018-01-01

Abstract

Frame semantics is a well-established framework to represent the meaning of natural language in computational terms. In this work, we aim to propose a quantitative measure of relatedness between pairs of frame instances. We test our method on a dataset of sentence pairs, highlighting the correlation between our metric and human judgments of semantic similarity. Furthermore, we propose an application of our measure for clustering frame instances to extract prototypical knowledge from natural language.
2018
Seventh Joint Conference on Lexical and Computational Semantics
New Orleans, Louisiana
2018
Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics
Association for Computational Linguistics
245
254
https://www.aclweb.org/anthology/S18-2029
Valerio Basile, Roque Lopez Condori, Elena Cabrio
File in questo prodotto:
File Dimensione Formato  
Measuring Frame Instance Relatedness.pdf

Accesso aperto

Tipo di file: PDF EDITORIALE
Dimensione 447.29 kB
Formato Adobe PDF
447.29 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/2318/1698289
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? ND
social impact