Current computational models of argument constructions typically represent their semantic content with hand-made formal structures. Here we present a distributional model implementing the idea that the meaning of a construction is in- timately related to the semantics of its typical verbs. First, we identify the typical verbs occurring with a given syntactic construction and build their distributional vectors. We then calculate the weighted centroid of these vectors in order to derive the distributional signature of a construction. In or- der to assess the goodness of our approach, we replicated the priming effect described by Johnson and Golberg (2013) as a function of the semantic distance between a construction and its prototypical verbs. Additional support for our view comes from a regression analysis showing that our distributional in- formation can be used to model behavioral data collected with a crowdsourced elicitation experiment.

Current computational models of argument constructions typically represent their semantic content with hand-made formal structures. Here we present a distributional model implementing the idea that the meaning of a construction is intimately related to the semantics of its typical verbs. First, we identify the typical verbs occurring with a given syntactic construction and build their distributional vectors. We then calculate the weighted centroid of these vectors in order to derive the distributional signature of a construction. In order to assess the goodness of our approach, we replicated the priming effect described by Johnson and Golberg (2013) as a function of the semantic distance between a construction and its prototypical verbs. Additional support for our view comes from a regression analysis showing that our distributional information can be used to model behavioral data collected with a crowdsourced elicitation experiment.

Modelling the Meaning of Argument Constructions with Distributional Semantics

Lebani Gianluca;
2017

Abstract

Current computational models of argument constructions typically represent their semantic content with hand-made formal structures. Here we present a distributional model implementing the idea that the meaning of a construction is in- timately related to the semantics of its typical verbs. First, we identify the typical verbs occurring with a given syntactic construction and build their distributional vectors. We then calculate the weighted centroid of these vectors in order to derive the distributional signature of a construction. In or- der to assess the goodness of our approach, we replicated the priming effect described by Johnson and Golberg (2013) as a function of the semantic distance between a construction and its prototypical verbs. Additional support for our view comes from a regression analysis showing that our distributional in- formation can be used to model behavioral data collected with a crowdsourced elicitation experiment.
The AAAI 2017 Spring Symposium on Computational Construction Grammar and Natural Language Understanding
File in questo prodotto:
File Dimensione Formato  
Lebani, Lenci - 2017 - Modelling the Meaning of Argument Constructions with Distributional Semantics.pdf

accesso aperto

Tipologia: Versione dell'editore
Licenza: Creative commons
Dimensione 657.37 kB
Formato Adobe PDF
657.37 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: http://hdl.handle.net/10278/3715942
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? ND
social impact