Search

Knowledge graphs (KGs) are widely used for modeling scholarly communication, performing scientometric analyses, and supporting a variety of intelligent services to explore the literature and predict research dynamics. However, they often suffer from incompleteness (e.g., missing affiliations, references, research topics), leading to a reduced scope and quality of the resulting analyses. This issue is usually tackled by computing knowledge graph embeddings (KGEs) and applying link prediction techniques. However, only a few KGE models are capable of taking weights of facts in the knowledge graph into account. Such weights can have different meanings, e.g. describe the degree of association or the degree of truth of a certain triple. In this paper, we propose the Weighted Triple Loss, a new loss function for KGE models that takes full advantage of the additional numerical weights on facts and it is even tolerant to incorrect weights. We also extend the Rule Loss, a loss function that is able to exploit a set of logical rules, in order to work with weighted triples. The evaluation of our solutions on several knowledge graphs indicates significant performance improvements with respect to the state of the art. Our main use case is the large-scale AIDA knowledge graph, which describes 21 million research articles. Our approach enables to complete information about affiliation types, countries, and research topics, greatly improving the scope of the resulting scientometrics analyses and providing better support to systems for monitoring and predicting research dynamics.

The continuous growth of scientific literature brings innovations and, at the same time, raises new challenges. One of them is related to the fact that its analysis has become difficult due to the high volume of published papers for which manual effort for annotations and management is required. Novel technological infrastructures are needed to help researchers, research policy makers, and companies to time-efficiently browse, analyse, and forecast scientific research. Knowledge graphs i.e., large networks of entities and relationships, have proved to be effective solution in this space. Scientific knowledge graphs focus on the scholarly domain and typically contain metadata describing research publications such as authors, venues, organizations, research topics, and citations. However, the current generation of knowledge graphs lacks of an explicit representation of the knowledge presented in the research papers. As such, in this paper, we present a new architecture that takes advantage of Natural Language Processing and Machine Learning methods for extracting entities and relationships from research publications and integrates them in a large-scale knowledge graph. Within this research work, we i) tackle the challenge of knowledge extraction by employing several state-of-the-art Natural Language Processing and Text Mining tools, ii) describe an approach for integrating entities and relationships generated by these tools, iii) show the advantage of such an hybrid system over alternative approaches, and vi) as a chosen use case, we generated a scientific knowledge graph including 109,105 triples, extracted from 26,827 abstracts of papers within the Semantic Web domain. As our approach is general and can be applied to any domain, we expect that it can facilitate the management, analysis, dissemination, and processing of scientific knowledge.

Springer Nature is the main publisher of scientific confer-ences in Computer Science and produces several well-known series of proceedings books, such as LNCS. The editorial team needs to take critical decisions about which conferences to publish as well as actively scan the horizon for identifying emerging ones. In this short paper, we present the Conference Dashboard, a new web application based on a large knowledge graph of scholarly data (1.3B triples) for assessing sci-entific conferences and informing editorial decisions.

The incompleteness of Knowledge Graphs (KGs) is a crucial issue affecting the quality of AI-based services. In the scholarly domain, KGs describing research publications typically lack important information, hindering our ability to analyse and predict research dynamics. In recent years, link prediction approaches based on Knowledge Graph Embedding models became the first aid for this issue. In this work, we present Trans4E, a novel embedding model that is particularly fit for KGs which include N to M relations with N ≫ M. This is typical for KGs that categorize a large number of entities (e.g., research articles, patents, persons) according to a relatively small set of categories. Trans4E was applied on two large-scale knowledge graphs, the Academia/Industry DynAmics (AIDA) and Microsoft Academic Graph (MAG), for completing the information about Fields of Study (e.g., ‘neural networks’, ‘machine learning’, ‘artificial intelligence’), and affiliation types (e.g., ‘education’, ‘company’, ‘government’), improving the scope and accuracy of the resulting data. We evaluated our approach against alternative solutions on AIDA, MAG, and four other benchmarks (FB15k, FB15k-237, WN18, and WN18RR). Trans4E outperforms the other models when using low embedding dimensions and obtains competitive results in high dimensions.

Ontologies of research areas are important tools for characterizing, exploring, and analyzing the research landscape. Some fields of research are comprehensively described by large-scale taxonomies, e.g., MeSH in Biology and PhySH in Physics. Conversely, current Computer Science taxonomies are coarse-grained and tend to evolve slowly. For instance, the ACM classification scheme contains only about 2K research topics and the last version dates back to 2012. In this paper, we introduce the Computer Science Ontology (CSO), a large-scale, automatically generated ontology of research areas, which includes about 14K topics and 162K semantic relationships. It was created by applying the Klink-2 algorithm on a very large data set of 16M scientific articles. CSO presents two main advantages over the alternatives: i) it includes a very large number of topics that do not appear in other classifications, and ii) it can be updated automatically by running Klink-2 on recent corpora of publications. CSO powers several tools adopted by the editorial team at Springer Nature and has been used to enable a variety of solutions, such as classifying research publications, detecting research communities, and predicting research trends. To facilitate the uptake of CSO, we have also released the CSO Classifier, a tool for automatically classifying research papers, and the CSO Portal, a Web application that enables users to download, explore, and provide granular feedback on CSO. Users can use the portal to navigate and visualize sections of the ontology, rate topics and relationships, and suggest missing ones. The portal will support the publication of and access to regular new releases of CSO, with the aim of providing a comprehensive resource to the various research communities engaged with scholarly data.

The identification of research topics and trends is an important scientometric activity, as it can help guide the direction of future research. In the Semantic Web area, initially topic and trend detection was primarily performed through qualitative, top-down style approaches, that rely on expert knowledge. More recently, data-driven, bottom-up approaches have been proposed that offer a quantitative analysis of the evolution of a research domain. In this paper, we aim to provide a broader and more complete picture of Semantic Web topics and trends by adopting a mixed methods methodology, which allows for the combined use of both qualitative and quantitative approaches. Concretely, we build on a qualitative analysis of the main seminal papers, which adopt a top-down approach, and on quantitative results derived with three bottom-up data-driven approaches (Rexplore, Saffron, PoolParty), on a corpus of Semantic Web papers published between 2006 and 2015. In this process, we both use the latter for 'fact-checking' on the former and also to derive key findings in relation to the strengths and weaknesses of top-down and bottom-up approaches to research topic identification. Although we provide a detailed study on the past decade of Semantic Web research, the findings and the methodology are relevant not only for our community but beyond the area of the Semantic Web to other research fields as well.

Ontologies of research areas have been proven to be useful resources for analysing and making sense of scholarly data. In this chapter, we present the Computer Science Ontology (CSO), which is the largest ontology of research areas in the field, and discuss a number of applications that build on CSO to support high-level tasks, such as topic classification, metadata extraction, and recommendation of books.

Scientific knowledge has been traditionally disseminated and preserved through research articles published in journals, conference proceedings, and online archives. However, this article-centric paradigm has been often criticized for not allowing to automatically process, categorize, and reason on this knowledge. An alternative vision is to generate a semantically rich and interlinked description of the content of research publications. In this paper, we present the Artificial Intelligence Knowledge Graph (AI-KG), a large-scale automatically generated knowledge graph that describes 820K research entities. AI-KG includes about 14M RDF triples and 1.2M reified statements extracted from 333K research publications in the field of AI, and describes 5 types of entities (tasks, methods, metrics, materials, others) linked by 27 relations. AI-KG has been designed to support a variety of intelligent services for analyzing and making sense of research dynamics, supporting researchers in their daily job, and helping to inform decision-making in funding bodies and research policymakers. AI-KG has been generated by applying an automatic pipeline that extracts entities and relationships using three tools: DyGIE++, Stanford CoreNLP, and the CSO Classifier. It then integrates and filters the resulting triples using a combination of deep learning and semantic technologies in order to produce a high-quality knowledge graph. This pipeline was evaluated on a manually crafted gold standard, yielding competitive results. AI-KG is available under CC BY 4.0 and can be downloaded as a dump or queried via a SPARQL endpoint.

Scientific conferences play a crucial role in the field of Computer Science by promoting the cross-pollination of ideas and technologies, fostering new collaborations, shaping scientific communities, and connecting research efforts from academia and industry. However, current systems for analysing research data do not provide a good representation of conferences. Specifically, these solutions do not allow to track research trends, to compare conferences in similar fields, and to analyse the involvement of industrial sectors. In order to address these limitations, we developed the AIDA Dashboard, a tool for exploring and making sense of scientific conferences which integrates statistical analysis, semantic technologies, and visual analytics.

Academia and industry are constantly engaged in a joint effort for producing scientific knowledge that will shape the society of the future. Analysing the knowledge flow between them and understanding how they influence each other is a critical task for researchers, governments, funding bodies, investors, and companies. However, current corpora are unfit to support large-scale analysis of the knowledge flow between academia and industry since they lack of a good characterization of research topics and industrial sectors. In this short paper, we introduce the Academia/Industry DynAmics (AIDA) Knowledge Graph, which characterizes 14M papers and 8M patents according to the research topics drawn from the Computer Science Ontology. 4M papers and 5M patents are also classified according to the type of the author’s affiliations (academy, industry, or collaborative) and 66 industrial sectors (e.g., automotive, financial, energy, electronics) obtained from DBpedia. AIDA was generated by an automatic pipeline that integrates several knowledge graphs and bibliographic corpora, including Microsoft Academic Graph, Dimensions, English DBpedia, the Computer Science Ontology, and the Global Research Identifier Database.

Understanding, monitoring, and predicting the flow of knowledge between academia and industry is of critical importance for a variety of stakeholders, including governments, funding bodies, researchers, investors, and companies. To this purpose, we introduce ResearchFlow, an approach that integrates semantic technologies and machine learning to quantifying the diachronic behaviour of research topics across academia and industry. ResearchFlow exploits the novel Academia/Industry DynAmics (AIDA) Knowledge Graph in order to characterize each topic according to the frequency in time of the related i) publications from academia, ii) publications from industry, iii) patents from academia, and iv) patents from industry. This representation is then used to produce several analytics regarding the academia/industry knowledge flow and to forecast the impact of research topics on industry. We applied ResearchFlow to a dataset of 3.5M papers and 2M patents in Computer Science and highlighted several interesting patterns. We found that 89.8% of the topics first emerge in academic publications, which typically precede industrial publications by about 5.6 years and industrial patents by about 6.6 years. However this does not mean that academia always dictates the research agenda. In fact, our analysis also shows that industrial trends tend to influence academia more than academic trends affect industry. We evaluated ResearchFlow on the task of forecasting the impact of research topics on the industrial sector and found that its granular characterization of topics improves significantly the performance with respect to alternative solutions.