Building Semantic Grams of Human Knowledge

Valentina Leone, Giovanni Siragusa, Luigi Di Caro, Roberto Navigli


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.
Anthology ID:
2020.lrec-1.366
Volume:
Proceedings of the Twelfth Language Resources and Evaluation Conference
Month:
May
Year:
2020
Address:
Marseille, France
Editors:
Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
2991–3000
Language:
English
URL:
https://aclanthology.org/2020.lrec-1.366
DOI:
Bibkey:
Cite (ACL):
Valentina Leone, Giovanni Siragusa, Luigi Di Caro, and Roberto Navigli. 2020. Building Semantic Grams of Human Knowledge. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 2991–3000, Marseille, France. European Language Resources Association.
Cite (Informal):
Building Semantic Grams of Human Knowledge (Leone et al., LREC 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.lrec-1.366.pdf