# Commonsense Knowledge Base Completion with Structural and Semantic Context Source: [Commonsense Knowledge Base Completion with Structural and Semantic Context]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:00:21.133Z Authors: Chaitanya Malaviya, Chandra Bhagavatula, Antoine Bosselut, Yejin Choi Published: 2019-10-07T17:16:04.000Z ## Abstract Automatic KB completion for commonsense knowledge graphs (e.g., ATOMIC and ConceptNet) poses unique challenges compared to the much studied conventional knowledge bases (e.g., Freebase). Commonsense knowledge graphs use free-form text to represent nodes, resulting in orders of magnitude more nodes compared to conventional KBs (18x more nodes in ATOMIC compared to Freebase (FB15K-237)). Importantly, this implies significantly sparser graph structures - a major challenge for existing KB completion methods that assume densely connected graphs over a relatively smaller set of nodes. In this paper, we present novel KB completion models that can address these challenges by exploiting the structural and semantic context of nodes. Specifically, we investigate two key ideas: (1) learning from local graph structure, using graph convolutional networks and automatic graph densification and (2) transfer learning from pre-trained language models to knowledge graphs for enhanced contextual representation of knowledge. We describe our method to incorporate information from both these sources in a joint model and provide the first empirical results for KB completion on ATOMIC and evaluation with ranking metrics on ConceptNet. Our results demonstrate the effectiveness of language model representations in boosting link prediction performance and the advantages of learning from local graph structure (+1.5 points in MRR for ConceptNet) when training on subgraphs for computational efficiency. Further analysis on model predictions shines light on the types of commonsense knowledge that language models capture well. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Knowledge Graph Completion on ConceptNet 100K (test)](): CKG completion; ConceptNet 100K (test); MRR: 43.6. - [CKG completion on ATOMIC subset (test)](): CKG completion; ATOMIC subset (test); MRR: 23.43. - [Relation Prediction on Malaviya 500 sampled triplets (test)](): Relation Prediction; Malaviya 500 sampled triplets (test); Count Predicted: 133. - [Knowledge Graph Completion on CN-100K](): Knowledge Graph Completion; CN-100K; MRR: 0.523. ## Original sources and implementation [Original paper]() [PDF]()