HGMAN: Multi-Hop and Multi-Answer Question Answering Based on Heterogeneous Knowledge Graph (Student Abstract)

Wang, Xu; Zhao, Shuai; Cheng, Bo; Han, Jiale; Li, Yingting; Yang, Hao; Nan, Guoshun

doi:10.1609/aaai.v34i10.7249

Cited by 5 publications

(10 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We choose GNN-based retrieval models as our baselines since they have achieved high performance across different KGQA datasets without additional information (query-answer paths or semantic parses). We experiment with three relevant KGQA retrieval techniques, namely, Embed-KGQA (Saxena et al, 2020), Rel-GCN (Wang et al, 2020a), and GlobalGraph (Wang et al, 2020b). We do not use baselines that require additional textual information to generate the heterogeneous graph, such as GraftNet (Sun et al, 2018) or PullNet (Sun et al, 2019) since this information is not available to us.…”

Section: Baselinesmentioning

confidence: 99%

“…Rel-GCN: The Rel-GCN approach of Wang et al (2020a) first constructs a smaller sub-graph K q for a given question, using PPR (Haveliwala, 2003) from the large base knowledge-graph, K. They encode the question q using PTLM as v q , and use TransE (Bordes et al, 2013) on K to obtain the node representations v e i for node e i in K. They concatenate the node embedding with the question-embedding e q , and then perform RGCN on K q to obtain their updated representations. These updated representations are used to score whether a given node is an answer or not.…”

Section: B1 Baselinesmentioning

confidence: 99%

“…Each model took around 3 hours to complete on a p3.8x large EC2 instance. Baselines: For Rel-GCN (Wang et al, 2020a), and GlobalGraph (Wang et al, 2020b), we use RoBERTa-BASE (Liu et al, 2019) to encode the question, and TransE embeddings to initialize the nodes (Bordes et al, 2013). We use the publicly available PyTorch-Geometric library (Fey and Lenssen, 2019) to implement RGCN (Schlichtkrull et al, 2018) for these two baselines.…”

Section: B2 Experimental Detailsmentioning

confidence: 99%

See 2 more Smart Citations

PerKGQA: Question Answering over Personalized Knowledge Graphs

Dutt¹,

Bhattacharjee²,

Gangadharaiah³

et al. 2022

Findings of the Association for Computational Linguistics: NAACL 2022

View full text Add to dashboard Cite

Previous studies on question answering over knowledge graphs have typically operated over a single knowledge graph (KG). This KG is assumed to be known a priori and is leveraged similarly for all users' queries during inference. However, such an assumption is not applicable to real-world settings, such as healthcare, where one needs to handle queries of new users over unseen KGs during inference. Furthermore, privacy concerns and high computational costs render it infeasible to query the single KG that has information about all users while answering a specific user's query. The above concerns motivate our question answering setting over personalized knowledge graphs (PERKGQA) where each user has restricted access to their KG. We observe that current state-of-the-art KGQA methods that require learning prior node representations fare poorly. We propose two complementary approaches, PATHCBR and PATHRGCN for PERKGQA. The former is a simple non-parametric technique that employs case-based reasoning, while the latter is a parametric approach using graph neural networks. Our proposed methods circumvent learning prior representations, can generalize to unseen KGs, and outperform strong baselines on an academic and an internal dataset by 6.5% and 10.5%.

show abstract

Section: Baselinesmentioning

confidence: 99%

Section: B1 Baselinesmentioning

confidence: 99%

Section: B2 Experimental Detailsmentioning

confidence: 99%

See 1 more Smart Citation

PerKGQA: Question Answering over Personalized Knowledge Graphs

Dutt¹,

Bhattacharjee²,

Gangadharaiah³

et al. 2022

Findings of the Association for Computational Linguistics: NAACL 2022

View full text Add to dashboard Cite

show abstract

“…Supported with a number of studies on graph representation learning (Kipf and Welling, 2017;Schlichtkrull et al, 2018;Wang et al, 2019a), graph neural network (GNN) shows its powerful ability in graph analysis. A massive number of GNN-based algorithms are designed to perform graph reasoning, such as R- GCN (Schlichtkrull et al, 2018), GRAFT-Net (Sun et al, 2018), HGMAN (Wang et al, 2020) and BAG (Cao et al, 2019), in which nodes update themselves by aggregating the information of neighboring nodes. A node can capture the unconnected node information through multiple GNN layers.…”

Section: Graph Neural Network Based Question Answeringmentioning

confidence: 99%

Modelling Long-distance Node Relations for KBQA with Global Dynamic Graph

Wang

Zhao

Han

et al. 2020

Proceedings of the 28th International Conference on Computational Linguistics

Self Cite

View full text Add to dashboard Cite

The structural information of Knowledge Bases (KBs) has proven effective to Question Answering (QA). Previous studies rely on deep graph neural networks (GNNs) to capture rich structural information, which may not model node relations in particularly long distance due to oversmoothing issue. To address this challenge, we propose a novel framework GlobalGraph, which models long-distance node relations from two views: 1) Node type similarity: GlobalGraph assigns each node a global type label and models long-distance node relations through the global type label similarity; 2) Correlation between nodes and questions: we learn similarity scores between nodes and the question, and model long-distance node relations through the sum score of two nodes. We conduct extensive experiments on two widely used multi-hop KBQA datasets to prove the effectiveness of our method.

show abstract

“…Although these methods prove e ectiveness, their processing steps and conversion process are relatively complex and meanwhile may involve expert knowledge or heuristic rules. Considering that answering multi-hop questions requires searching for reasoning paths, starting from the entity mentioned in question, and consisting of both the relations at each hop and intermediate entities, recent studies [12][13][14] have focused on the power of graph neural networks (GNNs) to solve the above limitations. ey often model the question directly to get a candidate entity graph, and then leverage graph neural network-based information propagation methods to update the node representations in the graph, which are used to choose the answer entities.…”

Section: Introductionmentioning

confidence: 99%

Edge-Aware Graph Neural Network for Multi-Hop Path Reasoning over Knowledge Base

Zhang

Jin

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Multi-hop path reasoning over knowledge base aims at finding answer entities for an input question by walking along a path of triples from graph structure data, which is a crucial branch in the knowledge base question answering (KBQA) research field. Previous studies rely on deep neural networks to simulate the way humans solve multi-hop questions, which do not consider the latent relation information contained in connected edges, and lack of measuring the correlation between specific relations and the input question. To address these challenges, we propose an edge-aware graph neural network for multi-hop path reasoning task. First, a query node is directly added to the candidate subgraph retrieved from the knowledge base, which constructs what we term a query graph. This graph construction strategy makes it possible to enhance the information flow between the question and the nodes for the subsequent message passing steps. Second, question-related information contained in the relations is added to the entity node representations during graph updating; meanwhile, the relation representations are updated. Finally, the attention mechanism is used to weight the contribution from neighbor nodes so that only the information of neighbor nodes related to the query can be injected into new node representations. Experimental results on MetaQA and PathQuestion-Large (PQL) benchmarks demonstrate that the proposed model achieves higher Hit@1 and F1 scores than the baseline methods by a large margin. Moreover, ablation studies show that both the graph construction and the graph update algorithm contribute to performance improvement.

show abstract

HGMAN: Multi-Hop and Multi-Answer Question Answering Based on Heterogeneous Knowledge Graph (Student Abstract)

Cited by 5 publications

References 4 publications

PerKGQA: Question Answering over Personalized Knowledge Graphs

PerKGQA: Question Answering over Personalized Knowledge Graphs

Modelling Long-distance Node Relations for KBQA with Global Dynamic Graph

Edge-Aware Graph Neural Network for Multi-Hop Path Reasoning over Knowledge Base

Contact Info

Product

Resources

About