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 evaluate the impact of the proposed resource on a semantic similarity task, showing significant improvements over state-of-the-art word embeddings. We release the complete semagram base and other data at http://nlp.uniroma1.it/semagrams.

Building semantic grams of human knowledge

Leone V.;Siragusa G.;Di Caro L.;Navigli R.
2020-01-01

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 evaluate the impact of the proposed resource on a semantic similarity task, showing significant improvements over state-of-the-art word embeddings. We release the complete semagram base and other data at http://nlp.uniroma1.it/semagrams.
2020
12th International Conference on Language Resources and Evaluation, LREC 2020
Palais du Pharo, fra (Online)
2020
LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings
European Language Resources Association (ELRA)
2991
3000
979-10-95546-34-4
https://aclanthology.org/2020.lrec-1.366
Concept representation; Lexical semantics; Semagrams; Word senses
Leone V.; Siragusa G.; Di Caro L.; Navigli R.
File in questo prodotto:
File Dimensione Formato  
2020.lrec-1.366.pdf

Accesso aperto

Tipo di file: PDF EDITORIALE
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.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/1997290
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 8
  • ???jsp.display-item.citation.isi??? ND
social impact