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
Venue:
*SEMEVAL
SIGs:
SIGLEX | SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
125–135
Language:
URL:
https://www.aclweb.org/anthology/S19-1014
DOI:
10.18653/v1/S19-1014
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/S19-1014.pdf