paper-with-me

Papers

Exploiting Hybrid Semantics of Relation Paths for Multi-hop Question Answering Over Knowledge Graphs

2022-09-02 · COLING 2022 10 · Zile Qiao, Wei Ye, Tong Zhang, Tong Mo, Weiping Li, Shikun Zhang

Answering natural language questions on knowledge graphs (KGQA) remains a great challenge in terms of understanding complex questions via multi-hop reasoning. Previous efforts usually exploit large-scale entity-related text corpora or knowledge graph (KG) embeddings as auxiliary information to facilitate answer selection. However, the rich semantics implied in off-the-shelf relation paths between entities is far from well explored. This paper proposes improving multi-hop KGQA by exploiting relation paths' hybrid semantics. Specifically, we integrate explicit textual information and implicit KG structural features of relation paths based on a novel rotate-and-scale entity link prediction framework. Extensive experiments on three existing KGQA datasets demonstrate the superiority of our method, especially in multi-hop scenarios. Further investigation confirms our method's systematical coordination between questions and relation paths to identify answer entities.

📄 PDF Abstract BibTeX arXiv:2209.00870

Code (0)

등록된 구현이 없습니다.

Tasks

Answer SelectionKnowledge GraphsLink PredictionMulti-hop Question AnsweringQuestion AnsweringRelation

Similar Papers 제목 키워드 기반

HybridGNN: Learning Hybrid Representation in Multiplex Heterogeneous Networks

2022-08-03 · Tiankai Gu, Chaokun Wang, Cheng Wu, Jingcao Xu 외

Recently, graph neural networks have shown the superiority of modeling the complex topological structures in heterogeneous network-based recommender systems. Due to the diverse interactions among nodes and abundant seman…

Recommendation Systems

Joint Semantics and Data-Driven Path Representation for Knowledge Graph Inference

2020-10-06 · Guanglin Niu, Bo Li, Yongfei Zhang, Yongpan Sheng 외

Inference on a large-scale knowledge graph (KG) is of great importance for KG applications like question answering. The path-based reasoning models can leverage much information over paths other than pure triples in the …

Link PredictionQuestion Answering

Inductive Meta-path Learning for Schema-complex Heterogeneous Information Networks

2023-07-08 · Shixuan Liu, Changjun Fan, Kewei Cheng, Yunfei Wang 외

Heterogeneous Information Networks (HINs) are information networks with multiple types of nodes and edges. The concept of meta-path, i.e., a sequence of entity types and relation types connecting two entities, is propose…

Relation

Global Relational Models of Source Code

2020-05-01 · ICLR 2020 1 · Vincent J. Hellendoorn, Charles Sutton, Rishabh Singh, Petros Maniatis 외

Models of code can learn distributed representations of a program's syntax and semantics to predict many non-trivial properties of a program. Recent state-of-the-art models leverage highly structured representations of p…

Inductive BiasProgram RepairVariable misuse

Learning on heterogeneous graphs using high-order relations

2021-03-29 · See Hian Lee, Feng Ji, Wee Peng Tay

A heterogeneous graph consists of different vertices and edges types. Learning on heterogeneous graphs typically employs meta-paths to deal with the heterogeneity by reducing the graph to a homogeneous network, guide ran…

RelationVocal Bursts Intensity Prediction