Abstract
Knowledge representation learning is a key step required for link prediction tasks with knowledge graphs (KGs). During the learning process, the semantics of each entity are embedded by a vector or a point in a feature space. The distance between these points is a measure of semantic similarity. However, in a KG, while two entities may have similar semantics in some relations, they have different semantics in others. It is ambiguous to assign a fixed distance to depict the variant semantic similarity of entities. To alleviate the semantic ambiguity in KGs, we design a new embedding approach named OpticE, which is derived from the well-known physical phenomenon of optical interference. It is a lightweight and relation-adaptive model based on coherence theory, in which each entity’s semantics vary automatically regarding different relations. In addition, a unique negative sampling method is proposed to combine the multimapping properties and self-adversarial learning during the training process. The experimental results obtained on practical KG benchmarks show that the OpticE model, with elegant structures, can compete with existing link prediction methods.- Anthology ID:
- 2022.coling-1.433
- 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:
- 4892–4901
- Language:
- URL:
- https://aclanthology.org/2022.coling-1.433
- DOI:
- Cite (ACL):
- Xiangyu Gui, Feng Zhao, Langjunqing Jin, and Hai Jin. 2022. OpticE: A Coherence Theory-Based Model for Link Prediction. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4892–4901, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
- Cite (Informal):
- OpticE: A Coherence Theory-Based Model for Link Prediction (Gui et al., COLING 2022)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2022.coling-1.433.pdf
- Data
- FB15k-237