Uncertainty-Aware Dynamic Knowledge Graphs for Reliable Question Answering

Recently, there has been an upsurge in the number of knowledge graphs (KG) that can only be accessed by experts. Non-expert users lack an adequate understanding of the queried knowledge graph's vocabulary and structure, as well as the syntax of the structured query language used to express the user's information needs. To increase the user base of these KGs, a set of Question Answering (QA) systems that use natural language to query these knowledge graphs have been introduced. However, finding a benchmark that accurately evaluates the quality of a QA system is a difficult task due to (1) the high degree of variation in the fine-grained properties among the existing benchmarks, (2) the static nature of the existing benchmarks versus the evolving nature of KGs, and (3) the limited number of KGs targeted by existing benchmarks, which hinders the usability of QA systems in real-world deployment over KGs that are different from those that were used in the evaluation of the QA systems. In this paper, we introduce Maestro, a benchmark generation system for question answering over knowledge graphs. Maestro can generate a new benchmark for any KG given the KG and, optionally, a text corpus that covers this KG. The benchmark generated by Maestro is guaranteed to cover all the properties of the natural language questions and queries that were encountered in the literature as long as the targeted KG includes these properties. Maestro also generates high-quality natural language questions with various utterances that are on par with manually-generated ones to better evaluate QA systems.

This systematic literature review investigates how evolvable knowledge graphs (KGs) enhance manufacturing. Evolvable KGs adapt to changing knowledge by leveraging machine learning algorithms and human expertise to improve decision-making, operational efficiency, and predictive maintenance capabilities beyond the capabilities of prevailing solutions enabled by dynamic KGs. This review maps the existing literature based on the stages of the KG development process. The main results are an updated model of the creation and maintenance of evolvable KGs in manufacturing and a literature-based synthesis of learning approaches for enabling KG evolution through knowledge processing and knowledge utilization. The results contribute to updating the KG development process model and synthesizing an understanding of evolvable KGs that utilize the observed learning approaches on knowledge processing to change KG relations and nodes, and three learning approaches through knowledge utilization (human-guided, machine-driven, and human-machine collaborative knowledge updates). Despite emerging advances, challenges persist in quality assurance, process planning, and integration of human expertise. The findings advocate addressing these issues to promote greater adoption and optimization of KGs in manufacturing. By deepening the understanding of how KGs can evolve through learning, this review sets a conceptual basis for future research to develop more dynamic and intelligent KG-based manufacturing systems.

There has been increasing research interest in inferring missing information from existing knowledge graphs (KGs) due to the emergence of a wide range of knowledge graph downstream applications such as question answering systems and search engines. Reasoning over knowledge graphs, which queries the correct entities only through a path consisting of multiple consecutive relations/hops from the starting entity, is an effective approach to do this task, but this topic has been rarely studied. As an attempt, the compositional training method equally treats the constructed multi-hop paths and one-hop relations to build training data, and then trains conventional knowledge graph completion models such as TransE in a compositional manner on the training data. However, it does not incorporate additional information along the paths during training, such as the intermediate entities and their types, which can be helpful to guide the reasoning towards the correct destination answers. Moreover, compositional training can only extend some existing models that can be composable, which significantly limits its applicability. Therefore, we design a novel model based on the recently proposed neural memory networks, which have large external memories and flexible writing/reading schemes, to address these problems. Specifically, we first introduce a single network layer, which is then used as the building block for a multi-layer neural network called TravNM, and a flexible memory updating method is developed to facilitate writing intermediate entity information during the multi-hop reasoning into memories. Finally, we conducted extensive experiments on large datasets, and the experimental results show the superiority of our proposed TravNM for reasoning over knowledge graphs with multiple hops.

While RDF was designed to make data easily readable by machines, it does not make data easily usable by end-users. Question Answering (QA) over Knowledge Graphs (KGs) is seen as the technology which is able to bridge this gap. It aims to build systems which are capable of extracting the answer to a user’s natural language question from an RDF dataset.In recent years, many approaches were proposed which tackle the problem of QA over KGs. Despite such efforts, it is hard and cumbersome to create a Question Answering system on top of a new RDF dataset. The main open challenge remains portability, i.e., the possibility to apply a QA algorithm easily on new and previously untested RDF datasets.In this publication, we address the problem of portability by presenting an architecture for a portable QA system. We present a novel approach called QAnswer KG, which allows the construction of on-demand QA systems over new RDF datasets. Hence, our approach addresses non-expert users in QA domain.In this paper, we provide the details of QA system generation process. We show that it is possible to build a QA system over any RDF dataset while requiring minimal investments in terms of training. We run experiments using 3 different datasets.To the best of our knowledge, we are the first to design a process for non-expert users. We enable such users to efficiently create an on-demand, scalable, multilingual, QA system on top of any RDF dataset.

BackgroundThe increasing aging population has led to a shortage of geriatric chronic disease caregiver, resulting in inadequate care for elderly people. In this global context, many older people rely on nonprofessional family care. The credibility of existing health websites cannot meet the needs of care. Specialized health knowledge bases such as SNOMED—CT and UMLS are also difficult for nonprofessionals to use. Furthermore, professional caregiver in elderly care institutions also face difficulty caring for multiple elderly people at the same time and working handovers. As a solution, we propose a smart care system for the elderly based on a knowledge graph.MethodFirst, we worked with professional caregivers to design a structured questionnaire to collect more than 100 pieces of care-related information for the elderly. Then, in the proposed system, personal information, smart device data, medical knowledge, and nursing knowledge are collected and organized into a dynamic knowledge graph. The system offers report generation, question answering, risk identification and data updating services. To evaluate the effectiveness of the system, we use the expert evaluation method to score the user experience.ResultsThe results of the study showed that compared to existing tools (health websites, archives and expert team consultation), the system achieved a score of 8 or more for basic information, health support and Dietary information. Some secondary evaluation indicators reached 9 and 10 points. This finding suggested that the system is superior to existing tools. We also present a case study to help the reader understand the role of the system.ConclusionThe smart care system provide personalized care guidelines for nonprofessional caregivers. It also makes the job easier for institutional caregivers. In addition, the system provides great convenience for work handover.

While conversing with chatbots, humans typically tend to ask many questions, a significant portion of which can be answered by referring to large-scale knowledge graphs (KG). While Question Answering (QA) and dialog systems have been studied independently, there is a need to study them closely to evaluate such real-world scenarios faced by bots involving both these tasks. Towards this end, we introduce the task of Complex Sequential QA which combines the two tasks of (i) answering factual questions through complex inferencing over a realistic-sized KG of millions of entities, and (ii) learning to converse through a series of coherently linked QA pairs. Through a labor intensive semi-automatic process, involving in-house and crowdsourced workers, we created a dataset containing around 200K dialogs with a total of 1.6M turns. Further, unlike existing large scale QA datasets which contain simple questions that can be answered from a single tuple, the questions in our dialogs require a larger subgraph of the KG. Specifically, our dataset has questions which require logical, quantitative, and comparative reasoning as well as their combinations. This calls for models which can: (i) parse complex natural language questions, (ii) use conversation context to resolve coreferences and ellipsis in utterances, (iii) ask for clarifications for ambiguous queries, and finally (iv) retrieve relevant subgraphs of the KG to answer such questions. However, our experiments with a combination of state of the art dialog and QA models show that they clearly do not achieve the above objectives and are inadequate for dealing with such complex real world settings. We believe that this new dataset coupled with the limitations of existing models as reported in this paper should encourage further research in Complex Sequential QA.

IoT devices generate substantial amounts of measurements and use many different formats to store this data. In order to make IoT devices interoperable, a number of ontologies have been developed, such as the Smart Applications REFerence (SAREF) ontology, to create knowledge graphs that can represent all kinds of measurements from IoT devices. We call the resulting knowledge graphs: IoT measurement knowledge graphs. In this thesis, we set out to investigate what differentiates IoT measurement knowledge graphs from regular knowledge graphs. In the first half, we describe in detail how to create IoT measurement knowledge graphs from real-world measurement data. In the second half, we investigate what happens when we use the graphs in different scenarios, with different methods and applications. In order to generate an IoT measurement knowledge graph, we create a mapping to transform the measurement data coming from IoT devices. We explore multiple ways to create this mapping and evaluate the resulting IoT measurement knowledge graph with competency questions. Using our mapping, we create OfficeGraph, by transforming IoT measurement data recorded over a year from 444 IoT devices located in an office building. This IoT measurement knowledge graph is validated by answering competency questions created with the support of the building owners, showing that we can answer questions we were not able to answer without it. Besides the entities, literals, and relations in knowledge graphs, the combination of these, the context of entities, provides additional knowledge. Therefore, if we want to use entities in knowledge graphs to train machine learning models, it would be a waste to take only the entities from the graph, because this would leave out information. Representation models, such as RDF2Vec and Graph Convolutional Networks (GCNs), can be used to learn (embedding) representations for entities that take context into account, creating a representation based on which relations, entities, and literals occur near the entity in the graph. We learn over IoT measurement knowledge graphs using multiple representation models and experiment with the effect of making more knowledge available to the representation models through semantic enrichment. This is done by making implicit information, such as (e.g.) consecutive measurements, explicitly available, by adding a relation between two measurements. Results show that the semantic enrichment has a positive effect on the learnability, based on the evaluation score, of the entity representations. Due to the dynamic nature of IoT measurement knowledge graphs, it is to be expected that new measurements are made after the initial IoT measurement knowledge graphs are created. Therefore, we investigate the possibility of estimating representations for new entities that are based on the existing entity representations. We introduce the embedding estimation method, which used the numerical attributes of entities, the measurement values, to find entities similar to the new entity. Then by averaging the embedding representations of those entities, it creates a new, estimated, embedding for the new entity. We perform experiments to test the embedding estimation method, and show that there is a trade-off between the amount of time saved by not re-training the entire pipeline, but also a decrease in accuracy, with the estimated embeddings. This thesis offers a focused research into IoT measurement knowledge graph. We provide insight into how IoT measurement knowledge graph can be created and how they differ from regular knowledge graphs, specifically in being numerical, dynamic, and shallow knowledge graphs. We suggest and validate remedies to the shallowness of IoT measurement knowledge graphs, through the semantic enrichments. Furthermore we show how the numerical aspect can be a strength, through the embedding estimation method, which can help with the dynamic nature of IoT measurement knowledge graph.

As a new generation technology representative of knowledge engineering, knowledge graph is a large-scale semantic network, which has natural advantages in extracting knowledge from multi-source heterogeneous information, complex and highly correlated knowledge representation and reasoning. Based on the analysis of the application status of the grid day-ahead scheduling optimization decision-making technology and the demand for improving the intelligent processing capability, the key technologies and methods for the application of knowledge graph in the grid day-ahead scheduling optimization decision-making are proposed. The key technologies, application ideas and process methods of knowledge graphs are analyzed from the aspects of the design of knowledge ontology framework in the field of day-to-day dispatching of power grids, high-quality phrase mining and entity recognition, relation extraction and knowledge fusion, and scene-based dynamic knowledge graph update. Finally, the application and challenges of knowledge graph in the field of grid day-ahead scheduling in the future are summarized and prospected.

In recent years, medical Question Answering (QA) systems have gained a lot of attentions, since they can not only help professionals make quick decisions, but also give ordinary people advice when they seek for helpful information. However, the interpretability and accuracy problems have plagued QA systems for a long time. In this paper, we propose a QA system, DSQA, based on knowledge graph for answering domain-specific medical questions. The data we use are from Electronic Medical Records (EMRs) that are complex and heterogeneous with varied qualities. We introduce doctor-in-the-loop mechanism to design the knowledge graph, which improves the interpretability and the accuracy of our QA system. For every natural-language question, we generate the answer with a hybrid of the traditional deep learning model and the reasoning on the knowledge graph. Finally, the answer is returned to the user in the format of a subgraph with corresponding natural-language sentences. Our system shows high interpretability and gives excellent performance according to the experiment results.

To solve the problem of insufficient feature representation ability and poor topological adaptability of traditional methods in fault location of complex power transmission and transformation systems, this study proposes an intelligent location framework that combines knowledge graph with GraphSAGE. Based on a four-layer architecture, a dynamic knowledge graph is constructed in real time through SCADA/PMU data, defining entities such as substations, lines, circuit breakers and their electrical connections, protection triggers and other relationships, and designing an incremental graph update mechanism. The model layer uses a double-layer GraphSAGE, combined with an LSTM aggregator to perform stratified sampling and dynamic edge weight adjustment on neighborhood time series measurement features. Joint cross-entropy and knowledge constraint loss are introduced in training to balance classification error and semantic consistency. The experiment generates 2000 fault cases based on the IEEE39 node system. The results show that the positioning accuracy of the proposed model in the IEEE 39-node system reaches 0.953. As the transition resistance gradually increases from 200 Ω to 2000 Ω, the accuracy of the proposed model changes from 0.953 to 0.943. As the signal-to-noise ratio changes from 5dB to 30dB, the accuracy changes from 0.920 to 0.955.. The semantic enhancement of the knowledge graph and the dynamic topological reasoning mechanism of GraphSAGE synergistically improve the robustness and real-time performance of the model, providing a high-precision solution for the intelligent operation and maintenance of the power transmission and transformation system.

Data-driven, knowledge-grounded neural conversation models are capable of generating more informative responses. However, these models have not yet demonstrated that they can zero-shot adapt to updated, unseen knowledge graphs. This paper proposes a new task about how to apply dynamic knowledge graphs in neural conversation model and presents a novel TV series conversation corpus (DyKgChat) for the task. Our new task and corpus aids in understanding the influence of dynamic knowledge graphs on responses generation. Also, we propose a preliminary model that selects an output from two networks at each time step: a sequence-to-sequence model (Seq2Seq) and a multi-hop reasoning model, in order to support dynamic knowledge graphs. To benchmark this new task and evaluate the capability of adaptation, we introduce several evaluation metrics and the experiments show that our proposed approach outperforms previous knowledge-grounded conversation models. The proposed corpus and model can motivate the future research directions.

A knowledge graph (KG) consists of numerous triples, in which each triple, i.e., (head entity, relation, tail entity), denotes a real-world assertion. Many large-scale KGs have been developed, e.g., general-purpose KGs Freebase and YAGO. Also, lots of domain-specific KGs are emerging, e.g., COVID-19 KGs, biomedical KGs, and agricultural KGs. By embedding KGs into low-dimensional vectors, i.e., representations of entities and relations, we could integrate KGs into machine learning models and enhance the performance of many prediction tasks, including search, recommendations, and question answering. During the construction, refinement, embedding, and application of KGs, a variety of KG learning algorithms have been developed to handle challenges in various real-world scenarios. Moreover, graph neural networks have also brought new opportunities to KG learning. This workshop aims to engage with active researchers from KG communities, recommendation communities, natural language processing communities, and other communities, and deliver state-of-the-art research insights into the core challenges in KG learning.

Over the past decade, Knowledge Graphs (KG) have emerged as a prominent repository for storing facts about the world in a linked data architecture. Providing machines with the capability of exploring such Knowledge Graphs and answering natural language questions over them, has been an active area of research. The purpose of this work, is to delve further into the research of retrieving information stored in KGs, based on the natural language questions posed by the user. Knowledge Graph Question Answering (KGQA) aims to produce a concise answer to a user question, such that the user is exempt from using KG vocabulary and overheads of learning a formal query language. Existing KGQA systems have achieved excellent results over Simple Questions, where the information required is limited to a single triple and a single formal query pattern. Our motivation is to improve the performance of KGQA over Complex Questions, where formal query patterns significantly vary, and a single triple is not confining for all the required information. Complex KGQA provides several challenges such as understanding semantics and syntactic structure of questions, Entity Linking, Relation Linking and Answer Representation. Lack of suitable datasets for complex question answering further adds to research gaps. Hence, in this thesis, we focus the research objective of laying the foundations for the advancement of the state-of-the-art for Complex Question Answering over Knowledge Graphs, by providing techniques to solve various challenges and provide resources to fill the research gaps. First, we propose Normalized Query Structure (NQS), which is a linguistic analyzer module that helps the QA system to detect inputs and intents and the relation between them in the users' question. NQS acts like an intermediate language between natural language questions and formal expressions to ease the process of query formulation for complex questions. We then developed a framework named LC-QuAD to generate large scale question answering dataset by reversing the process of question answering, thereby translating natural language questions from the formal query using intermediate templates. Our goal is to use this framework for high variations in the query patterns and create a large size dataset with minimum human effort. The first version of the dataset consists of 5,000 complex questions. By extending the LC-QuAD framework to support Reified KGs and crowd-sourcing, we published the second version of the dataset as LC-QuAD 2.0, consisting of 30,000 questions with their paraphrases and has higher complexity and new variations in the questions. To overcome the problem of Entity Linking and Relation Linking in KGQA, we develop EARL, a module performing these two tasks as a single joint task for complex question answering. We develop approaches for this module, first by formalizing the task as an instance of the Generalized Traveling Salesman Problem (GTSP) and the second approach uses machine learning to exploit the connection density between nodes in the Knowledge Graph. Lastly, we create another large scale dataset to answer verbalization and provide results for multiple baseline system s on it. The Verbalization dataset is introduced to make the system's response more human-like. The NQS based KGQA system was next to the best system in terms of accuracy on the QALD-5 dataset. We empirically prove that NQS is robust to tackle paraphrases of the questions. EARL achieves the state of the art results in Entity Linking and Relation Linking for question answering on several KGQA datasets. The dataset curated in this thesis has helped the research community to move forward in the direction of improving the accuracy of complex question answering as a task as other researchers too developed several KGQA systems and modules around these published datasets. With the large-scale datasets, we have encouraged the use of large scale machine learning, deep learning and emergence of new techniques to advance the state-of-the-art in complex question answering over knowledge graphs. We further developed core components for the KGQA pipeline to overcome the challenges of Question Understanding, Entity-Relation Linking and Answer Verbalization and thus achieve our research objective. All the proposed approaches mentioned in this thesis and the published resources are available at https://github.com/AskNowQA and are released under the umbrella project AskNow.

Knowledge graphs have shown increasing value in semantic search, intelligent Q&A, data analysis, natural language processing, visual understanding, IoT devices, etc. It is undeniable that knowledge graphs have become the mandatory path for the artificial intelligence fields development. However, the information contained in existing knowledge graphs is incomplete, which attracts a large number of researchers to enhance the completeness of knowledge graphs utilizing knowledge graph completion methods. Most traditional embedding-based knowledge graph completion models use structural information within data-rich triples from the knowledge graph is limited by the long-tail distribution of the relations in the triples. To address this problem, we propose a Bert-based knowledge graph completion algorithm for few-shot knowledge graphs, with the main goal of implementing the knowledge graph completion task with only a few sample triples of training instances. We improve the baseline model GMatching for handling few-shot knowledge graphs by introducing the Bert pre-trained linguistic representation model to enhance the semantic representation of entities and relations in the triples. Through experiments, we demonstrate that our improved model B-GMatching achieves good results.

Knowledge graph embedding (KGE) models represent each entity and relation of a knowledge graph (KG) with low-dimensional embedding vectors. These methods have recently been applied to KG link prediction and question answering over incomplete KGs (KGQA). KGEs typically create an embedding for each entity in the graph, which results in large model sizes on real-world graphs with millions of entities. For downstream tasks these atomic entity representations often need to be integrated into a multi stage pipeline, limiting their utility. We show that an off-the-shelf encoder-decoder Transformer model can serve as a scalable and versatile KGE model obtaining state-of-the-art results for KG link prediction and incomplete KG question answering. We achieve this by posing KG link prediction as a sequence-to-sequence task and exchange the triple scoring approach taken by prior KGE methods with autoregressive decoding. Such a simple but powerful method reduces the model size up to 98% compared to conventional KGE models while keeping inference time tractable. After finetuning this model on the task of KGQA over incomplete KGs, our approach outperforms baselines on multiple large-scale datasets without extensive hyperparameter tuning.