Abstract
To date, the most successful word, word sense, and concept modelling techniques have used large corpora and knowledge resources to produce dense vector representations that capture semantic similarities in a relatively low-dimensional space. Most current approaches, however, suffer from a monolingual bias, with their strength depending on the amount of data available across languages. In this paper we address this issue and propose Conception, a novel technique for building language-independent vector representations of concepts which places multilinguality at its core while retaining explicit relationships between concepts. Our approach results in high-coverage representations that outperform the state of the art in multilingual and cross-lingual Semantic Word Similarity and Word Sense Disambiguation, proving particularly robust on low-resource languages. Conception – its software and the complete set of representations – is available at https://github.com/SapienzaNLP/conception.- Anthology ID:
- 2020.coling-main.291
- Volume:
- Proceedings of the 28th International Conference on Computational Linguistics
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona, Spain (Online)
- Editors:
- Donia Scott, Nuria Bel, Chengqing Zong
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 3268–3284
- Language:
- URL:
- https://aclanthology.org/2020.coling-main.291
- DOI:
- 10.18653/v1/2020.coling-main.291
- Cite (ACL):
- Simone Conia and Roberto Navigli. 2020. Conception: Multilingually-Enhanced, Human-Readable Concept Vector Representations. In Proceedings of the 28th International Conference on Computational Linguistics, pages 3268–3284, Barcelona, Spain (Online). International Committee on Computational Linguistics.
- Cite (Informal):
- Conception: Multilingually-Enhanced, Human-Readable Concept Vector Representations (Conia & Navigli, COLING 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.coling-main.291.pdf
- Code
- sapienzanlp/conception
- Data
- ConceptNet, Senseval-2, Word Sense Disambiguation: a Unified Evaluation Framework and Empirical Comparison