A GRAPH FRAMEWORK FOR METAPHOR CREATION INTEGRATING KNOWLEDGE GRAPH CONSTRUCTION AND GENERATION

Recently, large-scale knowledge graphs (KGs) have become a key asset for search, analytics, recommendations and data integration. Large-scale KGs provide millions of facts about the real world. Each fact is composed as (subject, relation, object), e.g., the triplet (“Cristiano Ronaldo”, playFor, “Real Madrid”). However, these facts are blind to the temporal dimension. Actually, knowledge in practice is time-variant and many relations are only valid for a certain period of time. This phenomenon highlights the importance of building temporal knowledge graphs. In particular, knowledge in temporal KG is represented as (subject, relation, object, valid time), e.g., (“Cristiano Ronaldo”, playFor, “Real Madrid”, “[2009, 2018]”. However, research on temporal KG is very current and there are still many problems needed to be addressed. One obvious problem is that the size of temporal KG is still very small. For example, only 6.6% of the facts are time-aware in one of the largest knowledge graphs, YAGO3. In addition, 71% of people have no known place of birth, and 75% have no known nationality in Freebase. Furthermore, over 87.7% of the facts are uncovered in Japanese DBpedia compared with English DBpedia. Therefore, in this thesis, we study how to enlarge and enrich temporal knowledge graphs from three aspects, namely, temporal KG enrichment. In particular, we study the enrichment problem from the following aspects: (1) volume, (2) completeness, and (3) coverage.Our first solution is temporal knowledge harvesting which extracts temporal knowledge from free text directly. However, text corpus is noisy, and extracting structured temporal facts with high accuracy and coverage is very challenging. Inspired by pattern-based systems, we propose a temporal knowledge harvesting framework. In particular, we propose various techniques to extract temporal patterns, including corpus annotation, pattern generation, scoring and clustering. These techniques can reduce ambiguity in the text corpus and can improve both the accuracy and coverage of the extracted patterns. Second, we leverage the extracted patterns to harvest temporal knowledge. To improve the accuracy, we propose a parse-tree-based method. And to increase the coverage, we consider the relationships between tree components, including part of speech (POS), clause types, constituency and dependency. Experiments on real-world datasets verify the effectiveness of our proposed framework.Our second solution is temporal knowledge graph completion. Temporal KG completion is the task of inferring unobserved edges between entity pairs. Generally, temporal KG completion relies on the temporal KG embeddings technique, which learns the low-dimensional representations of all KG components. As research on temporal KG embedding is very current, we study both the embedding and the completion problems. In particular, we observe that contexts are extremely useful for learning the representations of entities and for inferring the unknown time intervals. As a result, we propose a context-aware embedding model for KG embeddings and a context-based temporal inference model for KG completion. In our embedding model, we not only capture factual plausibility as traditional methods did, but also propose a new measure on contexts, named temporal consistency. It measures how well the target entity interacts with its surrounding contexts on the temporal dimension. Our completion model is based on the embedding model, and further captures the interactions on the entity dimension. Extensive experiments verify the effectiveness of our models.Our third solution is temporal knowledge graph alignment which aims to discover the SameAs edges across two temporal KGs. Not like previous attribute-based alignment models, we further divide attribute facts into character facts, digit facts and time facts. In particular, we observe that the context information is extremely useful for the identification of the same entities. Therefore, we propose an alignment model on leveraging temporal contexts to represent entities. However, contexts of the same object can be very different. For example, the value of career predicate changed from “football player” to “coach” for the football player “Zidane”. This is because entities are evolving over time and thus the predicate values can be different. In our framework, we propose an alignment module that simulates the entity evolving process. Specifically, this module captures the interactions between contexts and aggregates context information to represent the entity. Lastly, we found that not all contexts are relevant, e.g., height v.s. career. Actually, only the relevant contexts are useful for capturing the evolving. Therefore, we propose a clustering approach for grouping relevant contexts together. Our experimental results validate the superiority of our proposed alignment model.

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 essential resources for many applications including Web search and question answering. As KGs are often automatically constructed, they may contain incorrect facts. Detecting them is a crucial, yet extremely expensive task. Prominent solutions detect and explain inconsistency in KGs with respect to accompanying ontologies that describe the KG domain of interest. Compared to machine learning methods they are more reliable and human-interpretable but scale poorly on large KGs. In this paper, we present a novel approach to dramatically speed up the process of detecting and explaining inconsistency in large KGs by exploiting KG abstractions that capture prominent data patterns. Though much smaller, KG abstractions preserve inconsistency and their explanations. Our experiments with large KGs (e.g., DBpedia and Yago) demonstrate the feasibility of our approach and show that it significantly outperforms the popular baseline.

Knowledge graphs exhibit a typical hierarchical structure and find extensive applications in various artificial intelligence domains. However, large-scale knowledge graphs need to be completed, which limits the performance of knowledge graphs in downstream tasks. Knowledge graph embedding methods have emerged as a primary solution to enhance knowledge graph completeness. These methods aim to represent entities and relations as low-dimensional vectors, focusing on handling relation patterns and multi-relation types. Researchers need to pay more attention to the crucial feature of hierarchical relationships in real-world knowledge graphs. We propose a novel knowledge graph embedding model called Hierarchy-Aware Paired Relation Vectors Knowledge Graph Embedding (HPRE) to bridge this gap. By leveraging the power of 2D coordinates, HPRE adeptly model relation patterns, multi-relation types, and hierarchical features in the knowledge graph. Specifically, HPRE employs paired relation vectors to capture the distinct characteristics of head and tail entities, facilitating a better fit for relational patterns and multi-relation scenarios. Additionally, HPRE employs angular coordinates to differentiate entities at various levels of the hierarchy, effectively representing the hierarchical nature of the knowledge graph. The experimental results show that the HPRE model can effectively learn the hierarchical features of the knowledge graph and achieve state-of-the-art experimental results on multiple real-world datasets for the link prediction task.

EASC: An exception-aware semantic compression framework for real-world knowledge graphs

Top-[formula omitted] star queries on knowledge graphs through semantic-aware bounding match scores

The Mapping Manuscript Migrations (MMM) project transformed three separate datasets relating to the history and provenance of medieval and Renaissance manuscripts into a unified knowledge graph. The source databases are: Schoenberg Database of Manuscripts, from the Schoenberg Institute for Manuscript Studies, University of Pennsylvania; Bibale, from the Institut de recherche et d’histoire des textes (IRHT-CNRS, Paris); and Medieval Manuscripts in Oxford Libraries, from the Bodleian Libraries, University of Oxford. The data consist of more than 20 million RDF triples which have been mapped to the MMM Data Model. The model combines classes and properties from CIDOC-CRM and FRBR, together with some specific MMM elements. The Knowledge Graph was created using the MMM data transformation pipeline. The MMM dataset is available from the Zenodo repository, and can be directly deployed on a SPARQL endpoint using a docker recipe. To test and demonstrate its usefulness, the MMM Knowledge Graph is in use in the MMM Semantic Portal: https://mappingmanuscriptmigrations.org.

Biomedical knowledge graphs (KGs), which can help with the understanding of complex biological systems and pathologies, have begun to play a critical role in medical practice and research. However, challenges remain in their embedding and use due to their complex nature and the specific demands of their construction. Existing studies often suffer from problems such as sparse and noisy datasets, insufficient modeling methods and non-uniform evaluation metrics. In this work, we established a comprehensive KG system for the biomedical field in an attempt to bridge the gap. Here, we introduced PharmKG, a multi-relational, attributed biomedical KG, composed of more than 500000 individual interconnections between genes, drugs and diseases, with 29 relation types over a vocabulary of ~8000 disambiguated entities. Each entity in PharmKG is attached with heterogeneous, domain-specific information obtained from multi-omics data, i.e. gene expression, chemical structure and disease word embedding, while preserving the semantic and biomedical features. For baselines, we offered nine state-of-the-art KG embedding (KGE) approaches and a new biological, intuitive, graph neural network-based KGE method that uses a combination of both global network structure and heterogeneous domain features. Based on the proposed benchmark, we conducted extensive experiments to assess these KGE models using multiple evaluation metrics. Finally, we discussed our observations across various downstream biological tasks and provide insights and guidelines for how to use a KG in biomedicine. We hope that the unprecedented quality and diversity of PharmKG will lead to advances in biomedical KG construction, embedding and application.

Domain-specific goal-oriented dialogue systems typically require modeling three types of inputs, namely, (i) the knowledge-base associated with the domain, (ii) the history of the conversation, which is a sequence of utterances, and (iii) the current utterance for which the response needs to be generated. While modeling these inputs, current state-of-the-art models such as Mem2Seq typically ignore the rich structure inherent in the knowledge graph and the sentences in the conversation context. Inspired by the recent success of structure-aware Graph Convolutional Networks (GCNs) for various NLP tasks such as machine translation, semantic role labeling, and document dating, we propose a memory-augmented GCN for goal-oriented dialogues. Our model exploits (i) the entity relation graph in a knowledge-base and (ii) the dependency graph associated with an utterance to compute richer representations for words and entities. Further, we take cognizance of the fact that in certain situations, such as when the conversation is in a code-mixed language, dependency parsers may not be available. We show that in such situations we could use the global word co-occurrence graph to enrich the representations of utterances. We experiment with four datasets: (i) the modified DSTC2 dataset, (ii) recently released code-mixed versions of DSTC2 dataset in four languages, (iii) Wizard-of-Oz style CAM676 dataset, and (iv) Wizard-of-Oz style MultiWOZ dataset. On all four datasets our method outperforms existing methods, on a wide range of evaluation metrics.

While there has been a trend in the last decades for publishing large-scale and highly-interconnected Knowledge Graphs (KGs), their users often get overwhelmed by the task of understanding their content as a result of their size and complexity. Data profiling approaches have been proposed to summarize large KGs into concise and meaningful representations, so that they can be better explored, processed, and managed. Profiles based on schema patterns represent each triple in a KG with its schema-level counterpart, thus covering the entire KG with profiles of considerable size. In this paper, we provide empirical evidence that profiles based on schema patterns, if explored with suitable mechanisms, can be useful to help users understand the content of big and complex KGs. ABSTAT provides concise pattern-based profiles and comes with faceted interfaces for profile exploration. Using this tool we present a user study based on query completion tasks. We demonstrate that users who look at ABSTAT profiles formulate their queries better and faster than users browsing the ontology of the KGs. The latter is a pretty strong baseline considering that many KGs do not even come with a specific ontology to be explored by the users. To the best of our knowledge, this is the first attempt to investigate the impact of profiling techniques on tasks related to knowledge graph understanding with a user study.

Knowledge Graphs (KGs) are playing an increasingly important role in advancing the intelligence of the Web. Fine-grained type entity inferencing in a KG is very useful for enriching Semantic Web search results and allowing queries with a well-defined result set. This thesis developed two approaches based on tensor modelling for fine-grained type entity inference. In the first approach, it developed methods for utilising both embedded knowledge inside KGs and linked entity supplementary information outside KGs to improve inference accuracy. In the second approach, this thesis exploits type hierarchical path sampling technique to minimize the computational complexity of large-scale KG factorization.

Retrieval-augmented generation (RAG) enhances the reasoning capabilities of large language models (LLMs) by incorporating external knowledge. Among available sources, knowledge graphs (KGs) offer a structured and reliable foundation for factual information, making them increasingly popular in efforts to improve reasoning faithfulness in RAG. Most existing KG-based RAG methods rely on LLMs to extract knowledge from KGs. However, these approaches often require costly fine-tuning and struggle to navigate deep graph structures, limiting their effectiveness in multi-hop reasoning tasks. To address these challenges, we propose Stepwise Contrastive Reasoning (SCR), a lightweight framework that integrates graph structure and textual context for efficient and interpretable RAG over KGs. SCR combines relational message passing layers to encode KG entities with a Transformer encoder for processing question text. It decomposes reasoning into a series of alignment steps. At each step, SCR compares the current topic entity and its neighbors with the question representation, selecting the most relevant entity as the next topic entity. The question is then updated with this entity's textual description. This process continues until the selected entity no longer changes, indicating that the answer entity has been reached. Through stepwise alignment, SCR enables compact models to perform faithful and interpretable reasoning over large-scale KGs. Extensive experiments on several widely used KGQA benchmarks demonstrate that SCR not only achieves state-of-the-art performance but also effectively boosts the capabilities of smaller language models to match those of LLMs.

Harnessing the unlimited potential of RNA-sequencing data requires efficient and scalable solutions. In this research, we explore the power of knowledge graphs to analyze variant-level information extracted from RNA-sequences of COVID-19 patients. We propose a unified knowledge graph specifically tailored to the real-world relationships amongst entities obtained from Variant Call Format (VCF) files, annotated VCF files using the SnpEff tool, and associated CADD scores files while also maintaining a level of generality that permits future extrapolation and expansion. Utilizing available graph storage such as Blazegraph, we establish a large, scalable knowledge graph containing billions of nodes and edges that not only enables efficient storage, querying, and dataset creation but also serves as a foundation for several downstream tasks. To demonstrate its versatility, we present two compelling case studies using two different subsets of the graph, one containing 73 million nodes and 112 million edges and the other graph containing 1 million nodes and 2 million edges and employ graph machine learning techniques for node classification tasks. Several challenges, such as efficient scalability, capturing real-world knowledge at a large scale, and attaining a Graph Neural Network (GNN) with good performance and evaluation metrics, have been considered and dealt with. We compare two GNN models, GraphSAGE and Graph Convolutional Network (GCN), to identify the range of raw scores it can belong to and the GraphSAGE model to identify the deleteriousness of a variant using different model hyperparameter settings. Through the experiments conducted, we demonstrate that neighborhood knowledge can tremendously aid the model in learning and that the GraphSAGE model outperforms GCN for the CADD category node classification task. By seamlessly integrating a variety of RNA-seq genomic information into a coherent knowledge graph framework, our approach not only addresses the immediate challenges of accessing and parsing variant-level analysis but also lays the groundwork for future advancements using knowledge graphs in genomic research. Finally, we demonstrate the workings of our tool named VariantKG and present usage scenarios, namely, graph enrichment, graph creation, and graph machine learning and inference.

Rule-enhanced iterative complementation for knowledge graph reasoning

We examine the embedding approach to reason new relational facts from a largescale knowledge graph and a text corpus. We propose a novel method of jointly embedding entities and words into the same continuous vector space. The embedding process attempts to preserve the relations between entities in the knowledge graph and the concurrences of words in the text corpus. Entity names and Wikipedia anchors are utilized to align the embeddings of entities and words in the same space. Large scale experiments on Freebase and a Wikipedia/NY Times corpus show that jointly embedding brings promising improvement in the accuracy of predicting facts, compared to separately embedding knowledge graphs and text. Particularly, jointly embedding enables the prediction of facts containing entities out of the knowledge graph, which cannot be handled by previous embedding methods. At the same time, concerning the quality of the word embeddings, experiments on the analogical reasoning task show that jointly embedding is comparable to or slightly better than word2vec (Skip-Gram).