Abstract
ATOMIC is a large-scale commonsense knowledge graph (CSKG) containing everyday if-then knowledge triplets, i.e., head event, relation, tail event. The one-hop annotation manner made ATOMIC a set of independent bipartite graphs, which ignored the numerous links between events in different bipartite graphs and consequently caused shortages in knowledge coverage and multi-hop paths. In this work, we aim to construct Dense-ATOMIC with high knowledge coverage and massive multi-hop paths. The events in ATOMIC are normalized to a consistent pattern at first. We then propose a CSKG completion method called Rel-CSKGC to predict the relation given the head event and the tail event of a triplet, and train a CSKG completion model based on existing triplets in ATOMIC. We finally utilize the model to complete the missing links in ATOMIC and accordingly construct Dense-ATOMIC. Both automatic and human evaluation on an annotated subgraph of ATOMIC demonstrate the advantage of Rel-CSKGC over strong baselines. We further conduct extensive evaluations on Dense-ATOMIC in terms of statistics, human evaluation, and simple downstream tasks, all proving Dense-ATOMIC’s advantages in Knowledge Coverage and Multi-hop Paths. Both the source code of Rel-CSKGC and Dense-ATOMIC are publicly available on https://github.com/NUSTM/Dense-ATOMIC.- Anthology ID:
- 2023.acl-long.742
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 13292–13305
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.742
- DOI:
- 10.18653/v1/2023.acl-long.742
- Cite (ACL):
- Xiangqing Shen, Siwei Wu, and Rui Xia. 2023. Dense-ATOMIC: Towards Densely-connected ATOMIC with High Knowledge Coverage and Massive Multi-hop Paths. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13292–13305, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Dense-ATOMIC: Towards Densely-connected ATOMIC with High Knowledge Coverage and Massive Multi-hop Paths (Shen et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2023.acl-long.742.pdf