PerKGQA: Question Answering over Personalized Knowledge Graphs

Abstract

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%.

Knowledge graph‐driven data processing for business intelligence

“…Variational reasoning based approaches were presented in Zhang et al (2018). While most of the algorithms for question answering assume the existence of a large monolithic knowledge graph, which is known a priori, in Dutt et al (2022) authors propose solutions that can leverage knowledge spread across multiple smaller knowledge graphs. The article states that the proposed algorithms, one parametric and one non‐parametric, can address concerns about privacy and high computational costs, as these can work with personalized knowledge graphs (PERKGQA), where a user has restricted access to individual graphs only.…”

Recommendations for Responding to System Security Incidents Using Knowledge Graph Embedding

“…Knowledge completion techniques utilizing query sentences and knowledge graph embeddings are under active research. Knowledge completion infers new triples from the query embeddings and the subject and object embeddings of the knowledge graph [32][33][34][35]. In addition, a knowledge graph completion method based on a transformer-based model is being actively studied.…”

Document Understanding Dataset and Evaluation (DUDE)

“…As a result of its ability to function as a natural language interface for various forms of data, this paradigm has been applied to other domains. For example, the question-answering approach is combined with modalities such as videos [44,13,14,28,17], images [99,3,29,68,7,8], speech [100,43], knowledge graphs [93,84,80,22,37], and maps [70,15]. Overall, the convergence of computer vision and NLP through the emergence of VQA tasks has also opened up new avenues for research in the DU field, with many DU datasets now including rich visual content alongside questions.…”