Processing knowledge graph-based complex questions through question decomposition and recomposition

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.

Complex Question Answering over Knowledge Graph (C-KGQA) seeks to solve complex questions using knowledge graphs. Currently, KGQA systems achieve great success in answering simple questions, while complex questions still present challenging issues. As a result, an increasing number of novel methods have been proposed to remedy this challenge. In this survey, we proposed two mainstream categories of methods for C-KGQA, which are divided according to their use for knowledge graph representation and construction, namely, graph metric (GM)-Based Methods and graph neural network (GNN)-based methods. Additionally, we also acknowledge the influence of ChatGPT, which has prompted further research into utilizing knowledge graphs as a knowledge source to assist in answering complex questions. We also introduced methods based on pre-trained models and knowledge graph joint reasoning. Furthermore, we have compiled research achievements from the past three years to make it easier for researchers with similar interests to obtain state-of-the-art research. Finally, we discussed the resources and evaluation methods for tackling C-KGQA tasks and summarized several research prospects in this field.

With the growing availability of different knowledge graphs in a variety of domains, question answering over knowledge graph (KG-QA) becomes a prevalent information retrieval approach. Current KG-QA methods usually resort to semantic parsing, search or neural matching models. However, they cannot well tackle increasingly long input questions and complex information needs. In this work, we propose a new KG-QA approach, leveraging the rich domain context in the knowledge graph. We incorporate the new approach with question and answer domain context descriptions. Specifically, for questions, we enrich them with users’ subsequent input questions within a session and expand the input question representation. For the candidate answers, we equip them with surrounding context structures, i.e., meta-paths within the targeting knowledge graph. On top of these, we design a cross-attention mechanism to improve the question and answer matching performance. An experimental study on real datasets verifies these improvements. The new approach is especially beneficial for specific knowledge graphs with complex questions.

C-KGE: Curriculum learning-based Knowledge Graph Embedding

Besides the challenge that a human can ask one question in many different ways, a key aspect in Question Answering approaches over Knowledge Graphs (KGQA) is to deal with the vast amount of information present in the knowledge graphs. Modern real-world knowledge graphs contain nearly millions of entities and relationships. Additionally, they are enriched with new facts every day. However, not all facts are relevant for answering particular questions, thus fostering several challenges to KGQA systems, which require interpretable and query-able data. One solution to filtering the extra data in knowledge graphs is to rely on graph summarization techniques. Graph-based summarization approaches aim to resize knowledge graphs to be more concise and precise by storing only relevant information. In this paper, we propose a framework named LAUREN that applies different summarization techniques on knowledge graphs to be used in KGQA systems. Our experiments show that LAUREN summarizes large knowledge graphs such as DBpedia by 2 million entities and its summarization still achieves the same performance on both question answering and linking tasks compared to the complete DBpedia.

Knowledge graphs encode semantic knowledge that can be exploited to enhance different data-driven tasks, e.g., query answering, data mining, ranking or recommendation. However, knowledge graphs may be incomplete, and relevant relations may be not included in the graph, affecting accuracy of these data-driven tasks. We tackle the problem of relation discovery in a knowledge graph, and devise $$\mathcal {KOI}$$KOI, a semantic based approach able to discover relations in portions of knowledge graphs that comprise similar entities. $$\mathcal {KOI}$$KOI exploits both datatype and object properties to compute the similarity among entities, i.e., two entities are similar if their datatype and object properties have similar values. $$\mathcal {KOI}$$KOI implements graph partitioning techniques that exploit similarity values to discover relations from knowledge graph partitions. We conduct an experimental study on a knowledge graph of TED talks with state-of-the-art similarity measures and graph partitioning techniques. Our observed results suggest that $$\mathcal {KOI}$$KOI is able to discover missing edges between related TED talks that cannot be discovered by state-of-the-art approaches. These results reveal that combining semantics encoded both in the similarity measures and in the knowledge graph structure, has a positive impact on the relation discovery problem.

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.

At present, the terahertz Q&A system can only answer simple single entity questions, so it is difficult for people to retrieve and obtain effective information. In order to deal with diversified questions in Terahertz field and realize the function of complex questions in Terahertz field, a multi-entity question answering model is proposed in this paper. To deal with complex problems in terahertz field, this paper proposes a multi-round Q&A method for multi-entity recognition, and adds entity discrimination to improve the accuracy of named entity recognition. The method in this paper achieves the F1 value of 68.24% in CCKS2019CKBQA test set and F1 value of 85.33% in Terahertz data set. The method in this paper implements complex questions in the Terahertz domain.

The representation learning of knowledge graph refers to embedding entities and relations in knowledge graph into a low-dimensional dense vector space. Existing knowledge graph embedding models mostly chose Euclidean Space as their vector space and consider each fact triple in knowledge graph independently. However, Euclidean Space is unable to represent knowledge effectively due to its strict constraints and mathematical expression. Besides, entities in knowledge graph are not isolated, while these models ignore the association between entities. To solve the problems above, we proposed a text-enhanced knowledge graph representation learning model in Hyperbolic Space. We utilize rich semantic information of entity description by using Transformer Encoder to enhance the ability of knowledge representation. Besides, we embed entities and relations into Hyperbolic Space, which can better capture hierarchical information of the knowledge graph. Experiments on benchmark dataset show that our method achieves better performance compared with other state-of-art methods.KeywordsKnowledge graphRepresentation learningEmbedding modelHyperbolic space

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.

Scoring functions (SFs), which measure the plausibility of triplets in knowledge graph (KG), have become the crux of KG embedding. Lots of SFs, which target at capturing different kinds of relations in KGs, have been designed by humans in recent years. However, as relations can exhibit complex patterns that are hard to infer before training, none of them can consistently perform better than others on existing benchmark data sets. In this paper, inspired by the recent success of automated machine learning (AutoML), we propose to automatically design SFs (AutoSF) for distinct KGs by the AutoML techniques. However, it is non-trivial to explore domain-specific information here to make AutoSF efficient and effective. We firstly identify a unified representation over popularly used SFs, which helps to set up a search space for AutoSF. Then, we propose a greedy algorithm to search in such a space efficiently. The algorithm is further sped up by a filter and a predictor, which can avoid repeatedly training SFs with same expressive ability and help removing bad candidates during the search before model training. Finally, we perform extensive experiments on benchmark data sets. Results on link prediction and triplets classification show that the searched SFs by AutoSF, are KG dependent, new to the literature, and outperform the state-of- the-art SFs designed by humans.

Relational graph neural networks have garnered particular attention to encode graph context in knowledge graphs (KGs). Although they achieved competitive performance on small KGs, how to efficiently and effectively utilize graph context for large KGs remains an open problem. To this end, we propose the Relation-based Embedding Propagation (REP) method. It is a post-processing technique to adapt pre-trained KG embeddings with graph context. As relations in KGs are directional, we model the incoming head context and the outgoing tail context separately. Accordingly, we design relational context functions with no external parameters. Besides, we use averaging to aggregate context information, making REP more computation-efficient. We theoretically prove that such designs can avoid information distortion during propagation. Extensive experiments also demonstrate that REP has significant scalability while improving or maintaining prediction quality. Particularly, it averagely brings about 10% relative improvement to triplet-based embedding methods on OGBL-WikiKG2 and takes 5%-83% time to achieve comparable results as the state-of-the-art GC-OTE.

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.

Knowledge graphs (KGs) are widely used in many real-world applications, such as information retrieval, question answering system, and personal recommendation. However, most KGs are suffering from the incompleteness problem. To deal with the task of link prediction, previous knowledge graph embedding methods require numerous reference instances for each relation. It is worth noting that most relations in KGs have only a few reference instances available. Existing works for few-shot link prediction evaluate the authenticity of triplets from a single relation perspective. In this paper, we propose Hybrid Matching Network (HMNet) for few-shot link prediction, evaluating triplets from entity and relation two perspectives. At the entity-aware matching network, HMNet uses attentive inductive embedding layer to aggregate entity features and relation-aware topology, and then provides entity-aware score to implement first perspective evaluation. At the relation-aware matching network, HMNet integrates feature attention mechanism to implement relation perspective evaluation. Experiments on two public datasets indicate that HMNet achieves promising performance in few-shot link prediction.

Question answering (QA) systems are increasingly deployed across domains. However, their reliability is undermined when retrieved evidence is incomplete, noisy, or uncertain. Existing knowledge graph (KG) based QA frameworks typically represent facts as static and deterministic, failing to capture the evolving nature of information and the uncertainty inherent in reasoning. We present a demonstration of uncertainty-aware dynamic KGs, a framework that combines (i) dynamic construction of evolving KGs, (ii) confidence scoring and uncertainty-aware retrieval, and (iii) an interactive interface for reliable and interpretable QA. Our system highlights how uncertainty modeling can make QA more robust and transparent by enabling users to explore dynamic graphs, inspect confidence-annotated triples, and compare baseline versus confidence-aware answers. The target users of this demo are clinical data scientists and clinicians, and we instantiate the framework in healthcare: constructing personalized KGs from electronic health records, visualizing uncertainty across patient visits, and evaluating its impact on a mortality prediction task. This use case demonstrates the broader promise of uncertainty-aware dynamic KGs for enhancing QA reliability in high-stakes applications.