The family of clause types known as 'support (or 'light') verb construction' (SVC) manifests a peculiar syntax-semantics interface if compared with ordinary verb constructions (OVC). If, in e.g. She laughed, the verb licenses an argument and assigns it a semantic role, syntacticians of every stripe nowadays agree that it is the noun laugh, in She gave a laugh, which fulfils the same function. The differences between the two types have been extensively discussed in the linguistics literature (systematic research started in the 1970s), less so in Computational Linguistics. This paper has two objectives. First, it will propose an innovative type of semantic role, which is termed Cognate Semantic Role (CSR) because the verb employed in the notation is etymologically related to the predicate licensing arguments. She laughed and She gave a laugh therefore express the same role >the-one-who-laughs<, assigned by laughed and a laugh respectively. Second, it will introduce a tool capable of extracting CSRs automatically from both OVCs and SVCs; thus a device will be used for detecting the construction type. CSRs offer a number of advantages for the for-malization of entailments and paraphrases and for Machine Translation.

Mirto, I. (2020). Natural Language Inference in Ordinary and Support Verb Constructions. In Y. Dong, E. Herrera-Viedma, K. Matsui, S. Omatu, A. González-Briones, S. Rodriguez (a cura di), Distributed Computing and Artificial Intelligence, 17th International Conference (pp. 124-133). Springer.

Natural Language Inference in Ordinary and Support Verb Constructions

Mirto, I
2020

Abstract

The family of clause types known as 'support (or 'light') verb construction' (SVC) manifests a peculiar syntax-semantics interface if compared with ordinary verb constructions (OVC). If, in e.g. She laughed, the verb licenses an argument and assigns it a semantic role, syntacticians of every stripe nowadays agree that it is the noun laugh, in She gave a laugh, which fulfils the same function. The differences between the two types have been extensively discussed in the linguistics literature (systematic research started in the 1970s), less so in Computational Linguistics. This paper has two objectives. First, it will propose an innovative type of semantic role, which is termed Cognate Semantic Role (CSR) because the verb employed in the notation is etymologically related to the predicate licensing arguments. She laughed and She gave a laugh therefore express the same role >the-one-who-laughs<, assigned by laughed and a laugh respectively. Second, it will introduce a tool capable of extracting CSRs automatically from both OVCs and SVCs; thus a device will be used for detecting the construction type. CSRs offer a number of advantages for the for-malization of entailments and paraphrases and for Machine Translation.
Settore L-LIN/01 - Glottologia E Linguistica
978-3-030-53829-3
https://www.springer.com/gp/book/9783030530358
Mirto, I. (2020). Natural Language Inference in Ordinary and Support Verb Constructions. In Y. Dong, E. Herrera-Viedma, K. Matsui, S. Omatu, A. González-Briones, S. Rodriguez (a cura di), Distributed Computing and Artificial Intelligence, 17th International Conference (pp. 124-133). Springer.
File in questo prodotto:
File Dimensione Formato  
Mirto.Natural Language Inference.pdf

Solo gestori archvio

Descrizione: Frontespizio, indice e contributo
Tipologia: Versione Editoriale
Dimensione 1.37 MB
Formato Adobe PDF
1.37 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

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: http://hdl.handle.net/10447/432713
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact