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;
2017-01-01
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 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.
| 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.
