Search

In scientific papers, it is common practice to cite other articles to substantiate claims, provide evidence for factual assertions, reference limitations, and research gaps, and fulfill various other purposes. When authors include a citation in a given sentence, there are two considerations they need to take into account: (i) where in the sentence to place the citation and (ii) which citation to choose to support the underlying claim. In this paper, we focus on the first task as it allows multiple potential approaches that rely on the researcher's individual style and the specific norms and conventions of the relevant scientific community. We propose two automatic methodologies that leverage transformers architecture for either solving a Mask-Filling problem or a Named Entity Recognition problem. On top of the results of the proposed methodologies, we apply ad-hoc Natural Language Processing heuristics to further improve their outcome. We also introduce s2orc-9K, an open dataset for fine-tuning models on this task. A formal evaluation demonstrates that the generative approach significantly outperforms five alternative methods when fine-tuned on the novel dataset. Furthermore, this model's results show no statistically significant deviation from the outputs of three senior researchers.

The use of transformer-based models like BERT for natural language processing has achieved remarkable performance across multiple domains. However, these models face challenges when dealing with very specialized domains, such as scientific literature. In this paper, we conduct a comprehensive analysis of knowledge injection strategies for transformers in the scientific domain, evaluating four distinct methods for injecting external knowledge into transformers. We assess these strategies in a single-label multi-class classification task involving scientific papers. For this, we develop a public benchmark based on 12k scientific papers from the AIDA knowledge graph, categorized into three fields. We utilize the Computer Science Ontology as our external knowledge source. Our findings indicate that most proposed knowledge injection techniques outperform the BERT baseline.

Online platforms, serving as the primary conduit for travelers to seek, compare, and secure travel accommodations, require a profound understanding of user dynamics to craft competitive and enticing offerings. Concurrently, recent advancements in Natural Language Processing, particularly large language models, have made substantial strides in capturing the complexity of human language. Simultaneously, knowledge graphs have become a formidable instrument for structuring and categorizing information. This paper introduces a cutting-edge deep learning methodology integrating large language models with domain-specific knowledge graphs to classify tourism offers. It aims at aiding hospitality operators in understanding their accommodation offerings’ market positioning, taking into account the visit propensity and user review ratings, with the goal of optimizing the offers themselves and enhancing their appeal. Comparative analysis against alternative methods on two datasets of London accommodation offers attests to our approach’s effectiveness, demonstrating superior results.

The tourism and hospitality sectors have become increasingly important in the last few years and the companies operating in this field are constantly challenged with providing new innovative services. At the same time, (big-) data has become the 'new oil' of this century and Knowledge Graphs are emerging as the most natural way to collect, refine, and structure this heterogeneous information. In this paper, we present a methodology for semi-automatic generating a Tourism Knowledge Graph (TKG), which can be used for supporting a variety of intelligent services in this space, and a new ontology for modelling this domain, the Tourism Analytics Ontology (TAO). Our approach processes and integrates data from Booking.com, Airbnb, DBpedia, and GeoNames. Due to its modular structure, it can be easily extended to include new data sources or to apply new enrichment and refinement functions. We report a comprehensive evaluation of the functional, logical, and structural dimensions of TKG and TAO.

In the last few years, chatbots have become mainstream solutions adopted in a variety of domains for automatizing communication at scale. In the same period, knowledge graphs have attracted significant attention from business and academia as robust and scalable representations of information. In the scientific and academic research domain, they are increasingly used to illustrate the relevant actors (e.g., researchers, institutions), documents (e.g., articles, patents), entities (e.g., concepts, innovations), and other related information. Following the same direction, this paper describes how to integrate conversational agents with knowledge graphs focused on the scholarly domain, a.k.a. Scientific Knowledge Graphs. On top of the proposed architecture, we developed AIDA-Bot, a simple chatbot that leverages a large-scale knowledge graph of scholarly data. AIDA-Bot can answer natural language questions about scientific articles, research concepts, researchers, institutions, and research venues. We have developed four prototypes of AIDA-Bot on Alexa products, web browsers, Telegram clients, and humanoid robots. We performed a user study evaluation with 15 domain experts showing a high level of interest and engagement with the proposed agent.

Classifying scientific articles, patents, and other documents according to the relevant research topics is an important task, which enables a variety of functionalities, such as categorising documents in digital libraries, monitoring and predicting research trends, and recommending papers relevant to one or more topics. In this paper, we present the latest version of the CSO Classifier (v3.0), an unsupervised approach for automatically classifying research papers according to the Computer Science Ontology (CSO), a comprehensive taxonomy of research areas in the field of Computer Science. The CSO Classifier takes as input the textual components of a research paper (usually title, abstract, and keywords) and returns a set of research topics drawn from the ontology. This new version includes a new component for discarding outlier topics and offers improved scalability. We evaluated the CSO Classifier on a gold standard of manually annotated articles, demonstrating a significant improvement over alternative methods. We also present an overview of applications adopting the CSO Classifier and describe how it can be adapted to other fields.

In the past few decades, we saw a proliferation of scientific articles available online. This data-rich environment offers several opportunities but also challenges, since it is problematic to explore these resources and identify all the relevant content. Hence, it is crucial that they are appropriately annotated with their relevant concepts so to increase their chance of being properly indexed and retrieved. In this paper, we present R-Classify, a web tool that assists users in identifying the most relevant concepts according to a large-scale ontology of research areas in the field of Computer Science.

Science communication has a number of bottlenecks that include the rising number of published research papers and its non-machine-accessible and document-based paradigm, which makes the exploration, reading, and reuse of research outcomes rather inefficient. Recently, Knowledge Graphs (KG), i.e., semantic interlinked networks of entities, have been proposed as a new core technology to describe and curate scholarly information with the goal to make it machine readable and understandable. However, the main drawback of the use of such a technology is that researchers are asked to manually annotate their research papers and add their contributions within the KGs. To address this problem, in this paper we propose SCICERO, a novel KG generation approach that takes in input text from research articles and generates a KG of research entities. SCICERO uses Natural Language Processing techniques to parse the content of scientific papers to discover entities and relationships, exploits state-of-the-art Deep Learning Transformer models to make sense and validate extracted information, and uses Semantic Web best practices to formally represent the extracted entities and relationships, making the written content of research papers machine-actionable. SCICERO has been tested on a dataset of 6.7M papers about Computer Science generating a KG of about 10M entities. It has been evaluated on a manually generated gold standard of 3,600 triples that cover three Computer Science subdomains (Information Retrieval, Natural Language Processing, and Machine Learning) obtaining remarkable results.

In the last few years, we have witnessed the emergence of several knowledge graphs that explicitly describe research knowledge with the aim of enabling intelligent systems for supporting and accelerating the scientific process. These resources typically characterize a set of entities in this space (e.g., tasks, methods, evaluation techniques, proteins, chemicals), their relations, and the relevant actors (e.g., researchers, organizations) and documents (e.g., articles, books). However, they are usually very partial representations of the actual research knowledge and may miss several relevant facts. In this paper, we introduce SciCheck, a new triple classification approach for completing scientific statements in knowledge graphs. SciCheck was evaluated against other state-of-the-art approaches on seven benchmarks, yielding excellent results. Finally, we provide a real-world use case and applied SciCheck to the Artificial Intelligence Knowledge Graph (AI-KG), a large-scale automatically-generated open knowledge graph including 1.2M statements extracted from the 333K most cited articles in the field of Artificial Intelligence, and generated a new version of this knowledge graph with 300K additional triples.

In recent years, we saw the emergence of several approaches for producing machine-readable, semantically rich, interlinked description of the content of research publications, typically encoded as knowledge graphs. A common limitation of these solutions is that they address a low number of articles, either because they rely on human experts to summarize information from the literature or because they focus on specific research areas. In this paper, we introduce the Computer Science Knowledge Graph (CS-KG), a large-scale knowledge graph composed by over 350M RDF triples describing 41M statements from 6.7M articles about 10M entities linked by 179 semantic relations. It was automatically generated and will be periodically updated by applying an information extraction pipeline on a large repository of research papers. CS-KG is much larger than all comparable solutions and offers a very comprehensive representation of tasks, methods, materials, and metrics in Computer Science. It can support a variety of intelligent services, such as advanced literature search, document classification, article recommendation, trend forecasting, hypothesis generation, and many others. CS-KG was evaluated against a benchmark of manually annotated statements, yielding excellent results.

Data lakes are repositories of data stored in natural/raw format. A data lake may include structured data from relational databases, semi-structured data (i.e., JSON, CSV), unstructured data (i.e., text data), or binary data (i.e., images, audio, video). It is usually built on top of cost-efficient infrastructures such as Hadoop, Amazon S3, MongoDB, ElasticSearch, etc. Several organisations rely on big data lakes for crucial tasks such as reporting, visualisation, advanced analytics, machine learning, and business intelligence. A major limitation of this solution is that without descriptive metadata and a mechanism to maintain it, such data tend to be noisy, making their management and analysis complex and time-consuming. Therefore, there is the need to add a semantic layer based on a formal ontology to describe the data and efficient mechanism to represent them as a knowledge graph. In this paper, we present a methodology to add a semantic layer to a data lake and thus obtain a knowledge graph that can support structured queries and advanced data exploration. We describe a practical implementation of a methodology applied to a data lake consisting of text data describing the online marketplace for lodging and tourism activities. We report statistics about the data lake and the resulting knowledge graph.

Research publishing companies need to constantly monitor and compare scientific journals and conferences in order to inform critical business and editorial decisions. Semantic Web and Knowledge Graph technologies are natural solutions since they allow these companies to integrate, represent, and analyse a large quantity of information from heterogeneous sources. In this paper, we present the AIDA Dashboard 2.0, an innovative system developed in collaboration with Springer Nature to analyse and compare scientific venues, now also available to the public. This tool builds on a knowledge graph which includes over 1.5B RDF triples and was produced by integrating information about 25M research articles from Microsoft Academic Graph, Dimensions, DBpedia, GRID, CSO, and INDUSO. It can produce sophisticated analytics and rankings that are not available in alternative systems. We discuss the advantages of this solution for the Springer Nature editorial process and present a user study involving 5 editors and 5 researchers, which yielded excellent results in terms of quality of the analytics and usability.

Academia and industry share a complex, multifaceted, and symbiotic relationship. Analyzing the knowledge flow between them, understanding which directions have the biggest potential, and discovering the best strategies to harmonize their efforts is a critical task for several stakeholders. Research publications and patents are an ideal medium to analyze this space, but current data sets of scholarly data cannot be used for such a purpose because they lack a high-quality characterization of the relevant research topics and industrial sectors. In this paper, we introduce the Academia/ Industry DynAmics (AIDA) Knowledge Graph, which describes 21 million publications and 8 million patents according to the research topics drawn from the Computer Science Ontology. 5.1 million publications and 5.6 million patents are further characterized according to the type of the author’s affiliations and 66 industrial sectors from the proposed Industrial Sectors Ontology (INDUSO). AIDA was generated by an automatic pipeline that integrates data from Microsoft Academic Graph, Dimensions, DBpedia, the Computer Science Ontology, and the Global Research Identifier Database. It is publicly available under CC BY 4.0 and can be downloaded as a dump or queried via a triplestore. We evaluated the different parts of the generation pipeline on a manually crafted gold standard yielding competitive results.

Scientific conferences are essential for developing active research communities, promoting the cross-pollination of ideas and technologies, bridging between academia and industry, and disseminating new findings. Analyzing and monitoring scientific conferences is thus crucial for all users who need to take informed decisions in this space. However, scholarly search engines and bibliometric applications only provide a limited set of analytics for assessing research conferences, preventing us from performing a comprehensive analysis of these events. In this paper, we introduce the AIDA Dashboard, a novel web application, developed in collaboration with Springer Nature, for analyzing and comparing scientific conferences. This tool introduces three major new features: 1) it enables users to easily compare conferences within specific fields (e.g., Digital Libraries) and time-frames (e.g., the last five years); 2) it characterises conferences according to a 14K research topics from the Computer Science Ontology (CSO); and 3) it provides several functionalities for assessing the involvement of commercial organizations, including the ability to characterize industrial contributions according to 66 industrial sectors (e.g., automotive, financial, energy, electronics) from the Industrial Sectors Ontology (INDUSO). We evaluated the AIDA Dashboard by performing both a quantitative evaluation and a user study, obtaining excellent results in terms of quality of the analytics and usability.

Objetivo: To determine the correlation between salivary glucose levels with fasting blood glucose, HbA1c, and C-peptide in patients with type 2 diabetes mellitus (T2DM). Materials and methods: This is a cross-sectional study performed at the Centro de Investigación en Diabetes, Obesidad y Nutrición (CIDON) in Lima, Peru, during 2021. Patients were categorized as those with good metabolic control (HbA1c<7 %), and poor metabolic control (HbA1c≥7 %). Baseline fasting blood glucose, as well as blood HbA1c and C-peptide values were measured. Salivary glucose was measured using the glucose oxidase method. Spearman’s correlation was used for determining an association between salivary glucose levels and fasting blood glucose, HbA1c, and C-peptide. Results: One-hundred and forty-two subjects with T2DM participated in the study. Salivary glucose was significantly higher in T2DM subjects with poor metabolic control (p<0.01). A weak positive correlation between salivary glucose and fasting blood glucose (r= 0.23, p= 0.04) and HbA1c (r= 0.26, p= 0.02) was observed in subjects with T2DM and poor metabolic control, and also a non-significant negative correlation (r=-0.08; p= 0.47) with C-peptide. Conclusions: Salivary glucose levels show significant and positive association with fasting blood glucose and HbA1c, but not with C-peptide in persons with T2DM and poor metabolic control. However, there are many factors that should be considered and analyzed in detail aiming to determine its potential use., Objetivo: Determinar la correlación entre la glucosa salival con la glucosa en ayunas, HbA1c y el péptido C en personas con Diabetes Mellitus tipo 2 (DM2). Materiales y métodos: Estudio transversal llevado a cabo en el Centro de Investigación en Diabetes, Obesidad y Nutrición (CIDON) en Lima, Perú durante el año 2021. Se categorizó en buen control metabólico (HbA1c<7 %) y mal control metabólico (HbA1c≥7 %). Se midió la glucosa basal, HbA1c y el péptido C en sangre. La glucosa salival se midió con el método glucosa oxidasa. La correlación de Spearman fue usada para determinar la asociación entre la glucosa salival con la glucosa en ayunas, HbA1c y el péptido- C. Resultados: Participaron un total de 142 personas con DM2. La concentración de glucosa salival fue significativamente más elevada en DM2 con mal control metabólico (p<0.01). Se observó una correlación positiva débil significativa entre la glucosa salival y la glucosa basal (r=0.23, p=0.04) y HbA1c (r=0.26, p=0.02) en DM2 con mal control metabólico y una correlación negativa insignificante (r=-0.08; p=0.47) con el péptido C. Conclusiones: La glucosa salival presenta una asociación significativa y positiva con la glucosa en sangre y la HbA1c, pero no con el péptido C en personas con DM2 con mal control metabólico. Sin embargo, hay muchos factores que deben ser considerados y analizados más a fondo para determinar su posible uso

Understanding the relationship between the composition of a research team and the potential impact of their research papers is crucial as it can steer the development of new science policies for improving the research enterprise. Numerous studies assess how the characteristics and diversity of research teams can influence their performance across several dimensions: ethnicity, internationality, size, and others. In this paper, we explore the impact of diversity in terms of the authors' expertise. To this purpose, we retrieved 114K papers in the field of Computer Science and analysed how the diversity of research fields within a research team relates to the number of citations their papers received in the upcoming 5 years. The results show that two different metrics we defined, reflecting the diversity of expertise, are significantly associated with the number of citations. This suggests that, at least in Computer Science, diversity of expertise is key to scientific impact.

The crucial task of analysing the complex dynamics of the research landscape and uncovering the latest insights from the scientific literature is of paramount importance to researchers, governments, and commercial organizations. Springer Nature, one of the leading academic publishers worldwide, plays a significant role in this domain and regularly integrates and processes a variety of data sources to inform strategic decisions. Since exploring the resulting data is a challenging task, in 2021 we developed AIDA-Bot, a chatbot that addresses inquiries about the research landscape by utilising a large-scale knowledge graph of scholarly data. This paper presents the novel AIDA-Bot 2.0, which can both 1) support a set of predetermined question types by automatically translating them to formal queries on the knowledge graph, and 2) answer open questions by summarising information from relevant articles. We evaluated the performance of AIDA-Bot 2.0 through a comparative assessment against alternative architectures and an extensive user study. The results indicate that the novel features provide more accurate information and an excellent user experience.