Towards interpretable, data-derived distributional meaning representations for reasoning: A dataset of properties and concepts

Pia Sommerauer, Antske Fokkens, Piek Vossen


Abstract
This paper proposes a framework for investigating which types of semantic properties are represented by distributional data. The core of our framework consists of relations between concepts and properties. We provide hypotheses on which properties are reflected in distributional data or not based on the type of relation. We outline strategies for creating a dataset of positive and negative examples for various semantic properties, which cannot easily be separated on the basis of general similarity (e.g. fly: seagull, penguin). This way, a distributional model can only distinguish between positive and negative examples through evidence for a target property. Once completed, this dataset can be used to test our hypotheses and work towards data-derived interpretable representations.
Anthology ID:
2019.gwc-1.12
Volume:
Proceedings of the 10th Global Wordnet Conference
Month:
July
Year:
2019
Address:
Wroclaw, Poland
Editors:
Piek Vossen, Christiane Fellbaum
Venue:
GWC
SIG:
SIGLEX
Publisher:
Global Wordnet Association
Note:
Pages:
85–98
Language:
URL:
https://aclanthology.org/2019.gwc-1.12
DOI:
Bibkey:
Cite (ACL):
Pia Sommerauer, Antske Fokkens, and Piek Vossen. 2019. Towards interpretable, data-derived distributional meaning representations for reasoning: A dataset of properties and concepts. In Proceedings of the 10th Global Wordnet Conference, pages 85–98, Wroclaw, Poland. Global Wordnet Association.
Cite (Informal):
Towards interpretable, data-derived distributional meaning representations for reasoning: A dataset of properties and concepts (Sommerauer et al., GWC 2019)
Copy Citation:
PDF:
https://aclanthology.org/2019.gwc-1.12.pdf