Boosting question answering over knowledge graph with reward integration and policy evaluation under weak supervision
Among existing knowledge graph based question answering (KGQA) methods, relation
supervision methods require labeled intermediate relations for stepwise reasoning. To avoid …
supervision methods require labeled intermediate relations for stepwise reasoning. To avoid …
Incorporating anticipation embedding into reinforcement learning framework for multi-hop knowledge graph question answering
H Cui, T Peng, F Xiao, J Han, R Han, L Liu - Information Sciences, 2023 - Elsevier
Multi-hop knowledge graph question answering (KGQA) aims to pinpoint answer entities by
reasoning across multiple triples in knowledge graphs (KGs). To enhance model …
reasoning across multiple triples in knowledge graphs (KGs). To enhance model …
Unrestricted multi-hop reasoning network for interpretable question answering over knowledge graph
Abstract Knowledge graphs significantly boost the answer retrieval quality for natural
language questions. The knowledge graph based question answering (KGQA) task returns …
language questions. The knowledge graph based question answering (KGQA) task returns …
Message passing for complex question answering over knowledge graphs
S Vakulenko, JD Fernandez Garcia, A Polleres… - Proceedings of the 28th …, 2019 - dl.acm.org
Question answering over knowledge graphs (KGQA) has evolved from simple single-fact
questions to complex questions that require graph traversal and aggregation. We propose a …
questions to complex questions that require graph traversal and aggregation. We propose a …
Improving embedded knowledge graph multi-hop question answering by introducing relational chain reasoning
Abstract Knowledge Graph Question Answering (KGQA) aims to answer user-questions from
a knowledge graph (KG) by identifying the reasoning relations between topic entity and …
a knowledge graph (KG) by identifying the reasoning relations between topic entity and …
Lego: Latent execution-guided reasoning for multi-hop question answering on knowledge graphs
Answering complex natural language questions on knowledge graphs (KGQA) is a
challenging task. It requires reasoning with the input natural language questions as well as …
challenging task. It requires reasoning with the input natural language questions as well as …
Hierarchical query graph generation for complex question answering over knowledge graph
Knowledge Graph Question Answering aims to automatically answer natural language
questions via well-structured relation information between entities stored in knowledge …
questions via well-structured relation information between entities stored in knowledge …
Retrieve-rewrite-answer: A kg-to-text enhanced llms framework for knowledge graph question answering
Despite their competitive performance on knowledge-intensive tasks, large language
models (LLMs) still have limitations in memorizing all world knowledge especially long tail …
models (LLMs) still have limitations in memorizing all world knowledge especially long tail …
Path-based multi-hop reasoning over knowledge graph for answering questions via adversarial reinforcement learning
H Cui, T Peng, R Han, J Han, L Liu - Knowledge-Based Systems, 2023 - Elsevier
Multi-hop knowledge graph question answering targets at pinpointing the answer entities by
inferring across multiple triples in knowledge graphs. To enhance model interpretability …
inferring across multiple triples in knowledge graphs. To enhance model interpretability …
Improving multi-hop question answering over knowledge graphs using knowledge base embeddings
Abstract Knowledge Graphs (KG) are multi-relational graphs consisting of entities as nodes
and relations among them as typed edges. Goal of the Question Answering over KG (KGQA) …
and relations among them as typed edges. Goal of the Question Answering over KG (KGQA) …