Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph

Xin Lv, Xu Han, Lei Hou, Juanzi Li, Zhiyuan Liu, Wei Zhang, Yichi Zhang, Hao Kong, Suhui Wu


Abstract
Multi-hop reasoning has been widely studied in recent years to seek an effective and interpretable method for knowledge graph (KG) completion. Most previous reasoning methods are designed for dense KGs with enough paths between entities, but cannot work well on those sparse KGs that only contain sparse paths for reasoning. On the one hand, sparse KGs contain less information, which makes it difficult for the model to choose correct paths. On the other hand, the lack of evidential paths to target entities also makes the reasoning process difficult. To solve these problems, we propose a multi-hop reasoning model over sparse KGs, by applying novel dynamic anticipation and completion strategies: (1) The anticipation strategy utilizes the latent prediction of embedding-based models to make our model perform more potential path search over sparse KGs. (2) Based on the anticipation information, the completion strategy dynamically adds edges as additional actions during the path search, which further alleviates the sparseness problem of KGs. The experimental results on five datasets sampled from Freebase, NELL and Wikidata show that our method outperforms state-of-the-art baselines. Our codes and datasets can be obtained from https://github.com/THU-KEG/DacKGR.
Anthology ID:
2020.emnlp-main.459
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5694–5703
Language:
URL:
https://aclanthology.org/2020.emnlp-main.459
DOI:
10.18653/v1/2020.emnlp-main.459
Bibkey:
Cite (ACL):
Xin Lv, Xu Han, Lei Hou, Juanzi Li, Zhiyuan Liu, Wei Zhang, Yichi Zhang, Hao Kong, and Suhui Wu. 2020. Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5694–5703, Online. Association for Computational Linguistics.
Cite (Informal):
Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph (Lv et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.459.pdf
Video:
 https://slideslive.com/38938756
Code
 THU-KEG/DacKGR
Data
NELL