Peiyun Wu

TL;DR: This paper presents a path-based embedding strategy combined with the Gaussian embedding method to maintain better local relevance of embedded nodes and shows that GLP2Gauss has competitive performance on node classification and link prediction for networks compared with off-the-shelf network representation models.

TL;DR: This paper proposes a novel semi-supervised graph representation learning method RUGCN by leveraging explicit unsupervised information into training and introduces a broadcast cross-entropy function to ensure ranking smoothing run in harmony with Laplacian smoothing.

Abstract: Semantic parsing, as an important approach to question answering over knowledge bases (KBQA), transforms a question into the complete query graph for further generating the correct logical query. Existing semantic parsing approaches mainly focus on relations matching with paying less attention to the underlying internal structure of questions (e.g., the dependencies and relations between all entities in a question) to select the query graph. In this paper, we present a relational graph convolutional network (RGCN)-based model gRGCN for semantic parsing in KBQA. gRGCN extracts the global semantics of questions and their corresponding query graphs, including structure semantics via RGCN and relational semantics (label representation of relations between entities) via a hierarchical relation attention mechanism. Experiments evaluated on benchmarks show that our model outperforms off-the-shelf models.