Word senses are typically defined with textual definitions for human consumption and, in computational lexicons, put in context via lexical-semantic relations such as synonymy, antonymy, hypernymy, etc. In this paper we embrace a radically different paradigm that provides a slot-filler structure, called {``}semagram{''}, to define the meaning of words in terms of their prototypical semantic information. We propose a semagram-based knowledge model composed of 26 semantic relationships which integrates features from a range of different sources, such as computational lexicons and property norms. We describe an annotation exercise regarding 50 concepts over 10 different categories and put forward different automated approaches for extending the semagram base to thousands of concepts. We finally evaluated the impact of the proposed resource on a semantic similarity task, showing significant improvements over state-of-the-art word embeddings.
Building Semantic Grams of Human Knowledge / Leone, Valentina and Siragusa, Giovanni and Di Caro, Luigi and Navigli, Roberto. - ELETTRONICO. - (2020), pp. 2991-3000. (Intervento presentato al convegno LREC 2020: 2th Conference on Language Resources and Evaluation tenutosi a Marseille nel 11–16 May 2020).
Building Semantic Grams of Human Knowledge
Leone, Valentina;
2020
Abstract
Word senses are typically defined with textual definitions for human consumption and, in computational lexicons, put in context via lexical-semantic relations such as synonymy, antonymy, hypernymy, etc. In this paper we embrace a radically different paradigm that provides a slot-filler structure, called {``}semagram{''}, to define the meaning of words in terms of their prototypical semantic information. We propose a semagram-based knowledge model composed of 26 semantic relationships which integrates features from a range of different sources, such as computational lexicons and property norms. We describe an annotation exercise regarding 50 concepts over 10 different categories and put forward different automated approaches for extending the semagram base to thousands of concepts. We finally evaluated the impact of the proposed resource on a semantic similarity task, showing significant improvements over state-of-the-art word embeddings.File | Dimensione | Formato | |
---|---|---|---|
2020.lrec-1.366.pdf
accesso aperto
Tipo:
Versione (PDF) editoriale
Licenza:
Licenza per Accesso Aperto. Creative Commons Attribuzione - Non commerciale (CCBYNC)
Dimensione
5.3 MB
Formato
Adobe PDF
|
5.3 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.