Abstract
In this paper we introduce the TTCSℰ, a linguistic resource that relies on BabelNet, NASARI and ConceptNet, that has now been used to compute the conceptual similarity between concept pairs. The conceptual representation herein provides uniform access to concepts based on BabelNet synset IDs, and consists of a vector-based semantic representation which is compliant with the Conceptual Spaces, a geometric framework for common-sense knowledge representation and reasoning. The TTCSℰ has been evaluated in a preliminary experimentation on a conceptual similarity task.- Anthology ID:
- W17-1912
- Volume:
- Proceedings of the 1st Workshop on Sense, Concept and Entity Representations and their Applications
- Month:
- April
- Year:
- 2017
- Address:
- Valencia, Spain
- Editors:
- Jose Camacho-Collados, Mohammad Taher Pilehvar
- Venue:
- SENSE
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 96–101
- Language:
- URL:
- https://aclanthology.org/W17-1912
- DOI:
- 10.18653/v1/W17-1912
- Cite (ACL):
- Enrico Mensa, Daniele P. Radicioni, and Antonio Lieto. 2017. TTCSℰ: a Vectorial Resource for Computing Conceptual Similarity. In Proceedings of the 1st Workshop on Sense, Concept and Entity Representations and their Applications, pages 96–101, Valencia, Spain. Association for Computational Linguistics.
- Cite (Informal):
- TTCSℰ: a Vectorial Resource for Computing Conceptual Similarity (Mensa et al., SENSE 2017)
- PDF:
- https://preview.aclanthology.org/jeptaln-2024-ingestion/W17-1912.pdf