Search

Knowledge base question answering aims to answer a question over a knowledge base. Multi-hop knowledge base question answering is a challenging task because it requires multi-step reasoning according to the question to get the answer. Existing models infer the answer over a static subgraph or attend to different parts of the question through an intermediate signal. The former obtains limited semantic information, and the latter provides limited reasoning due to the weak supervision signal. In this paper, we eliminate the limitation of static subgraph reasoning by dynamically expanding subgraphs, which connect the question and subgraph to form a joint subgraph. We then adjust the dynamic subgraph to enable reasoning at each step. Specifically, at each step, the question connects different subgraphs, respects the context while paying attention to a specific part of the question, generates a strong intermediate signal, acts on the subsequent reasoning, and finally obtains a correct answer. A large number of experiments on three datasets show that our method performs better than previous state-of-the-art models. [ABSTRACT FROM AUTHOR]

Knowledge Graph (KG) is widely used for recommendation tasks due to its rich semantic information and external structure. Current knowledge graph recommendation models are insufficient for the learning of user–item interactive behaviors as well as external knowledge, and ignore the noise information in KG. To alleviate these limitations, we present a Collaborative Relation-aware Attention Network with Differentiable sampling (DCRAN) that can fully learn user–item interactions and knowledge graphs, and accurately select recommendation-related entities in KG. Specifically, DCRAN explicitly learns the embeddings of users and items and encodes them into collaborative interaction signals, which are used as guidance signals to extract knowledge. Furthermore, DCRAN emphasizes the importance of KG relations and constructs a relation-aware attention network to learn the representation of items in KG. Most importantly, DCRAN applies a differentiable sampling strategy on entities, which can reduce triplets that have a negative effect on recommendation. Experimental results on three public datasets manifest the effectiveness of DCRAN. [ABSTRACT FROM AUTHOR]