Concept-driven representation learning model for knowledge graph completion

Y Xiang, H He, Z Yu, Y Huang - Expert Systems with Applications, 2024 - Elsevier
Abstract Knowledge graph completion (KGC) aims to address the problem of incomplete
knowledge graph (KG) by predicting missing entities or relations. Representation learning …

Knowledge Graph Compression Enhances Diverse Commonsense Generation

EJ Hwang, V Thost, V Shwartz, T Ma - Proceedings of the 2023 …, 2023 - aclanthology.org
Generating commonsense explanations requires reasoning about commonsense
knowledge beyond what is explicitly mentioned in the context. Existing models use …

Cyclical Contrastive Learning Based on Geodesic for Zero-shot Cross-lingual Spoken Language Understanding

X Cheng, Z Zhu, B Yang, X Zhuang, H Li… - Findings of the …, 2024 - aclanthology.org
Owing to the scarcity of labeled training data, Spoken Language Understanding (SLU) is still
a challenging task in low-resource languages. Therefore, zero-shot cross-lingual SLU …

Context-Aware Commonsense Knowledge Graph Reasoning With Path-Guided Explanations

Y Pan, J Liu, T Zhao, L Zhang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Commonsense knowledge graphs (CKGs) store massive commonsense knowledge as
triples whose nodes consist of free-form texts. CKG reasoning aims to predict missing nodes …

ATAP: Automatic Template-Augmented Commonsense Knowledge Graph Completion via Pre-Trained Language Models

F Zhang, Y Ding, J Cheng - … of the 2024 Conference on Empirical …, 2024 - aclanthology.org
The mission of commonsense knowledge graph completion (CKGC) is to infer missing facts
from known commonsense knowledge. CKGC methods can be roughly divided into two …

Efficient Knowledge Infusion via KG-LLM Alignment

Z Jiang, L Zhong, M Sun, J Xu, R Sun, H Cai… - arXiv preprint arXiv …, 2024 - arxiv.org
To tackle the problem of domain-specific knowledge scarcity within large language models
(LLMs), knowledge graph-retrievalaugmented method has been proven to be an effective …

KNOWCOMP POKEMON Team at DialAM-2024: A Two-Stage Pipeline for Detecting Relations in Dialogical Argument Mining

Z Zheng, Z Wang, Q Zong, Y Song - arXiv preprint arXiv:2407.19740, 2024 - arxiv.org
Dialogical Argument Mining (DialAM) is an important branch of Argument Mining (AM).
DialAM-2024 is a shared task focusing on dialogical argument mining, which requires us to …

[PDF][PDF] HiHo: A Hierarchical and Homogenous Subgraph Learning Model for Knowledge Graph Relation Prediction

J Ma, Y Ma, F Zhang, Y Wang, X Luo, C Li, Y Qiao - semantic-web-journal.net
Relation prediction in Knowledge Graphs (KGs) aims to anticipate the connections between
entities. While both transductive and inductive models are incorporated for context …