Unsupervised Knowledge Graph Generation Using Semantic Similarity Matching
Lixian Liu, Amin Omidvar, Zongyang Ma, Ameeta Agrawal, Aijun An
Abstract
Knowledge Graphs (KGs) are directed labeled graphs representing entities and the relationships between them. Most prior work focuses on supervised or semi-supervised approaches which require large amounts of annotated data. While unsupervised approaches do not need labeled training data, most existing methods either generate too many redundant relations or require manual mapping of the extracted relations to a known schema. To address these limitations, we propose an unsupervised method for KG generation that requires neither labeled data nor manual mapping to the predefined relation schema. Instead, our method leverages sentence-level semantic similarity for automatically generating relations between pairs of entities. Our proposed method outperforms two baseline systems when evaluated over four datasets.- Anthology ID:
- 2022.deeplo-1.18
- Volume:
- Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing
- Month:
- July
- Year:
- 2022
- Address:
- Hybrid
- Venue:
- DeepLo
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 169–179
- Language:
- URL:
- https://aclanthology.org/2022.deeplo-1.18
- DOI:
- 10.18653/v1/2022.deeplo-1.18
- Cite (ACL):
- Lixian Liu, Amin Omidvar, Zongyang Ma, Ameeta Agrawal, and Aijun An. 2022. Unsupervised Knowledge Graph Generation Using Semantic Similarity Matching. In Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing, pages 169–179, Hybrid. Association for Computational Linguistics.
- Cite (Informal):
- Unsupervised Knowledge Graph Generation Using Semantic Similarity Matching (Liu et al., DeepLo 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.deeplo-1.18.pdf
- Code
- lixianliu12/kgss
- Data
- DBpedia, TACRED