Learning Graph Embeddings from WordNet-based Similarity Measures
Andrey Kutuzov, Mohammad Dorgham, Oleksiy Oliynyk, Chris Biemann, Alexander Panchenko
Abstract
We present path2vec, a new approach for learning graph embeddings that relies on structural measures of pairwise node similarities. The model learns representations for nodes in a dense space that approximate a given user-defined graph distance measure, such as e.g. the shortest path distance or distance measures that take information beyond the graph structure into account. Evaluation of the proposed model on semantic similarity and word sense disambiguation tasks, using various WordNet-based similarity measures, show that our approach yields competitive results, outperforming strong graph embedding baselines. The model is computationally efficient, being orders of magnitude faster than the direct computation of graph-based distances.- Anthology ID:
- S19-1014
- Volume:
- Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Editors:
- Rada Mihalcea, Ekaterina Shutova, Lun-Wei Ku, Kilian Evang, Soujanya Poria
- Venue:
- *SEM
- SIGs:
- SIGLEX | SIGSEM
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 125–135
- Language:
- URL:
- https://aclanthology.org/S19-1014
- DOI:
- 10.18653/v1/S19-1014
- Cite (ACL):
- Andrey Kutuzov, Mohammad Dorgham, Oleksiy Oliynyk, Chris Biemann, and Alexander Panchenko. 2019. Learning Graph Embeddings from WordNet-based Similarity Measures. In Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019), pages 125–135, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Learning Graph Embeddings from WordNet-based Similarity Measures (Kutuzov et al., *SEM 2019)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/S19-1014.pdf