Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs

Woojeong Jin, Meng Qu, Xisen Jin, Xiang Ren


Abstract
Knowledge graph reasoning is a critical task in natural language processing. The task becomes more challenging on temporal knowledge graphs, where each fact is associated with a timestamp. Most existing methods focus on reasoning at past timestamps and they are not able to predict facts happening in the future. This paper proposes Recurrent Event Network (RE-Net), a novel autoregressive architecture for predicting future interactions. The occurrence of a fact (event) is modeled as a probability distribution conditioned on temporal sequences of past knowledge graphs. Specifically, our RE-Net employs a recurrent event encoder to encode past facts, and uses a neighborhood aggregator to model the connection of facts at the same timestamp. Future facts can then be inferred in a sequential manner based on the two modules. We evaluate our proposed method via link prediction at future times on five public datasets. Through extensive experiments, we demonstrate the strength of RE-Net, especially on multi-step inference over future timestamps, and achieve state-of-the-art performance on all five datasets.
Anthology ID:
2020.emnlp-main.541
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6669–6683
Language:
URL:
https://www.aclweb.org/anthology/2020.emnlp-main.541
DOI:
10.18653/v1/2020.emnlp-main.541
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.emnlp-main.541.pdf