Abstract
Combining two graphs requires merging the nodes which are counterparts of each other. In this process errors occur, resulting in incorrect merging or incorrect failure to merge. We find a high prevalence of such errors when using AskNET, an algorithm for building Knowledge Graphs from text corpora. AskNET node matching method uses string similarity, which we propose to replace with vector embedding similarity. We explore graph-based and word-based embedding models and show an overall error reduction of from 56% to 23.6%, with a reduction of over a half in both types of incorrect node matching.- Anthology ID:
- D19-5321
- Volume:
- Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13)
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong
- Venue:
- TextGraphs
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 172–176
- Language:
- URL:
- https://aclanthology.org/D19-5321
- DOI:
- 10.18653/v1/D19-5321
- Cite (ACL):
- Ida Szubert and Mark Steedman. 2019. Node Embeddings for Graph Merging: Case of Knowledge Graph Construction. In Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13), pages 172–176, Hong Kong. Association for Computational Linguistics.
- Cite (Informal):
- Node Embeddings for Graph Merging: Case of Knowledge Graph Construction (Szubert & Steedman, TextGraphs 2019)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/D19-5321.pdf