For the last decade, distributional semantics has been an active area of research to address the problem of understanding the semantics of words in natural language. The core principal of the distributional semantic approach is that the linguistic context surrounding a given word, which is represented as a vector, provides important information about its meaning. In this paper we investigate the possibility to exploit Combinatory Categorial Grammar (CCG) categories as syntactic features to be relevant for characterizing the context vector and hence the meaning of words. We find that the CCG categories can enhance the representation of verb meaning
CCG categories for Distributional Semantics Models / Paramita, Paramita; Bernardi, Raffaella. - (2013), pp. 467-474. ((Intervento presentato al convegno RANLP 2013 tenutosi a Bulgaria nel 7-13 Settembre 2013.
CCG categories for Distributional Semantics Models.
Paramita, Paramita;Bernardi, Raffaella
2013-01-01
Abstract
For the last decade, distributional semantics has been an active area of research to address the problem of understanding the semantics of words in natural language. The core principal of the distributional semantic approach is that the linguistic context surrounding a given word, which is represented as a vector, provides important information about its meaning. In this paper we investigate the possibility to exploit Combinatory Categorial Grammar (CCG) categories as syntactic features to be relevant for characterizing the context vector and hence the meaning of words. We find that the CCG categories can enhance the representation of verb meaningI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione