CLOct 14, 2022

Dense-ATOMIC: Towards Densely-connected ATOMIC with High Knowledge Coverage and Massive Multi-hop Paths

arXiv:2210.07621v2229 citationsh-index: 6Has Code
Originality Incremental advance
AI Analysis

This work addresses the issue of sparse connections in commonsense knowledge graphs for AI researchers, but it is incremental as it builds on an existing dataset with a new completion method.

The paper tackled the problem of ATOMIC, a commonsense knowledge graph, having limited knowledge coverage and multi-hop paths due to its one-hop annotation, by constructing Dense-ATOMIC using a completion method called Rel-CSKGC, resulting in improved performance over baselines as shown in automatic and human evaluations.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes