Knowledge Is Flat: A Seq2Seq Generative Framework for Various Knowledge Graph Completion

Chen Chen, Yufei Wang, Bing Li, Kwok-Yan Lam


Abstract
Knowledge Graph Completion (KGC) has been recently extended to multiple knowledge graph (KG) structures, initiating new research directions, e.g. static KGC, temporal KGC and few-shot KGC. Previous works often design KGC models closely coupled with specific graph structures, which inevitably results in two drawbacks: 1) structure-specific KGC models are mutually incompatible; 2) existing KGC methods are not adaptable to emerging KGs. In this paper, we propose KG-S2S, a Seq2Seq generative framework that could tackle different verbalizable graph structures by unifying the representation of KG facts into “flat” text, regardless of their original form. To remedy the KG structure information loss from the “flat” text, we further improve the input representations of entities and relations, and the inference algorithm in KG-S2S. Experiments on five benchmarks show that KG-S2S outperforms many competitive baselines, setting new state-of-the-art performance. Finally, we analyze KG-S2S’s ability on the different relations and the Non-entity Generations.
Anthology ID:
2022.coling-1.352
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
4005–4017
Language:
URL:
https://aclanthology.org/2022.coling-1.352
DOI:
Bibkey:
Cite (ACL):
Chen Chen, Yufei Wang, Bing Li, and Kwok-Yan Lam. 2022. Knowledge Is Flat: A Seq2Seq Generative Framework for Various Knowledge Graph Completion. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4005–4017, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Knowledge Is Flat: A Seq2Seq Generative Framework for Various Knowledge Graph Completion (Chen et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.352.pdf
Code
 chenchens190009/kg-s2s
Data
FB15k-237ICEWS