Chapter 11. Neuro-Symbolic Semantic Reasoning

Humans have astounding reasoning capabilities. They can learn from very few examples while providing explanations for their decision-making process. In contrast, deep learning techniques–even though robust to noise and very effective in generalizing across several fields including machine vision, natural language understanding, speech recognition, etc. –require large amounts of data and are mostly unable to provide explanations for their decisions. Attaining human-level robust reasoning requires combining sound symbolic reasoning with robust connectionist learning. However, connectionist learning uses low-level representations–such as embeddings–rather than symbolic representations. This challenge constitutes what is referred to as the Neuro-Symbolic gap. A field of study to bridge this gap between the two paradigms has been called neuro-symbolic integration or neuro-symbolic computing. This chapter aims to present approaches that contribute towards bridging the Neuro-Symbolic gap specifically in the Semantic Web field, RDF Schema (RDFS) and EL+ reasoning and to discuss the benefits and shortcomings of neuro-symbolic reasoning.

Organisation and Maintenance of Library Authority Files in Russia and Abroad

The article provides review of foreign and domestic publications on the problems of creation, development and use of authority files (AF) of names of persons, names of organizations, geographical names and other objects both at the international, national and regional levels. The paper presents analysis of the foreign experience of AF maintenance. The authors note that, due to the availability of universal collections and qualified specialists, AF formation abroad is usually carried out by national libraries. A substantive analysis of foreign publications has shown that national AFs (NAF) are characterized by data variability and diversity of approaches. The authors studied the experience of successful combination of NAF created according to different methods within the framework of the international corporate project — Virtual International Authority File (VIAF). The article notes that most of the Russian libraries do not use AF, since AF, created in republican and regional scientific libraries, as a rule, are not publicly available. At the same time, creation by a separate library of its own AF leads to high labour and material costs, and the formation of a large number of AF leads to the variability of the AFs created for the same objects. The authors conclude that for efficient use of AFs within the country, it is necessary to apply unified methods and rules for creation of authority records. Another way out is the application of the Semantic Web technology, which allows linking AFs created according to different methods. It is necessary to make maximum use of existing dictionaries or create dictionaries based on the World Wide Web Consortium (W3C), Resource Description Framework (RDF), RDF Schema (RDFS) and Web Ontology Language (OWL) standards.

The SPHN Ecosystem Towards FAIR Data

Health-related data originating from diverse sources are commonly stored in manifold databases and formats, making it difficult to find, access and gather data for research purposes. In addition, so-called secondary use scenarios for health data are usually hindered by local data codes, missing dictionaries and the lack of metadata and context descriptions. Following the FAIR principles (Findable, Accessible, Interoperable and Reusable), we developed a decentralized infrastructure to overcome these hurdles and enable collaborative research by making the meaning of health-related data understandable to both, humans and machines. This infrastructure is currently being implemented in the realm of the Swiss Personalized Health Network (SPHN), a research infrastructure initiative for enabling the use and exchange of health-related data for research in Switzerland. The SPHN ecosystem for FAIR data consists of the SPHN Dataset (semantic definitions), the SPHN RDF Schema (linkage and transport of the semantics in a machine-readable format), a project RDF template, extensive guidelines and conventions on how to generate SPHN RDF schema, a Terminology Service (converter of clinical terminologies in RDF), and a Quality Assurance Framework (automated data validation with SHACLs and SPARQLs). The SPHN ecosystem has been built in a way that it can easily be adapted and extended by any SPHN project to fit individual needs. By providing such a national ecosystem, SPHN supports researchers in generating, processing and sharing FAIR data.

Research on E-Science - Serverless Semantic E-Science Framework (SSE-SF)

Serverless implementation for a semantic e-science framework (SSe-SF) is all about pushing code to a compute service and networking with third party services and APIs to get the work done. The underlying infrastructure both hardware and software are hidden from the user. Serverless semantic e-science framework (SSe-SF) includes Knowledge Search and Navigation, Identity Management, URI/ Content Negotiation, RDF & RDF Schema annotated information resources, Shared Ontologies, Read-only Onto-Repository & Vocabulary, Onto-learning and merging, Semantic reasoners and Semantic data storage. SSe-SF is applied on computing the Outcome bases education attainment (OBE) calculation.

PENGEMBANGAN WEB SEMANTIK SILSILAH KELUARGA KAWITAN ARYA BELOG

Tujuan dari penelitian ini adalah membantu masyarakat dalam menampilkan informasi silsilah keluarga dan pura dari kawitan Arya Belog. Informasi silsilah keluarga kawitan tersebut dapat digunakan oleh sistem lain dengan menggunakan RDF dan RDF Schema. Dalam membuat sebuah file RDF digunakan standarisasi metadata dari CIDOC CRM dalam menentukan atribut-atribut pada database. Hasil akhir dari pengembangan ini berupa sistem Web Semantik Silsilah Keluarga Kawitan Arya Belog. Untuk proses pengujian, dilakukan empat tahap proses pengujian yaitu diantaranya uji white box, uji black box, uji ahli media yang menyatakan interface, performance, dan ability sistem sudah sesuai. Hasil uji ahli isi memperoleh nilai persentase 95,5 % dengan kriteria sangat sesuai dan uji respon pengguna yang menyatakan sistem sudah tepat dalam memberi informasi terkait kawitan Arya Belog. Hasil dari uji respon pengguna memperoleh nilai positif diatas rata-rata yaitu diantaranya 1,239 kategori daya tarik, 1,150 kategori kejelasan, 1,225 kategori efisiensi, 1,267 kategori ketepatan, 1,317 kategori stimulasi, dan 1,183 kategori kebaruan.

Pengembangan Web Semantik Silsilah Keluarga Kawitan Pasek Gelgel dengan Metode Pencarian Forward Chaining

Silsilah kawitan pada dasarnya merupakan sarana bagi masyarakat Hindu untuk menghormati para leluhurnya. Terdapat beberapa silsilah di Bali sehingga jika terdapat suatu aplikasi web yang memerlukan data antar silsilah, maka dibutuhkan suatu skema yang memungkinkan terhubungnya silsilah dari masing – masing sistem tersebut yaitu RDF Schema untuk mendukung penerapan web semantik. Pada proses pencarian menggunakan metode Forward Chaining. Penelitian ini bertujuan: (1) Mengetahui rancangan dan implementasi web silsilah kawitan Pasek Gelgel.(2) Mengetahui respon pengguna web silsilah keluarga kawitan Pasek Gelgel. Penelitian ini diharapkan mampu memberikan informasi tentang kawitan leluhurnya dan keturunan – keturunan selanjutnya. Jenis penelitian ini adalah penelitian dan pengembangan (Research and Development) dengan model penelitian waterfall. Untuk proses pengujian, dilakukan lima (5) jenis pengujian yaitu: (1) uji whitebox (2) uji blackbox(3) uji akurasi metode (4) uji ahli media (5) uji respon pengguna.

Semantic Extension for the Linked Data Based on Semantically Enhanced Annotation and Reasoning

Linked Data, a new form of knowledge representation and publishing described by RDF, can provide more precise and comprehensible semantic structures. However, the current RDF Schema (RDFS) and SPARQL-based query strategy cannot fully express the semantics of RDF since they cannot unleash the implicit semantics between linked entities, so they cannot unleash the potential of Linked Data. To fill this gap, this chapter first defines a new semantic annotating and reasoning method which can extend more implicit semantics from different properties and proposes a novel general Semantically-Extended Scheme for Linked Data Sources to realize the semantic extension over the target Linked Data source. Moreover, in order to effectively return more information in the process of semantic data retrieval, we then design a new querying model which extends the SPARQL pattern. Lastly, experimental results show that our proposal has advantages over the initial Linked Data source and can return more valid results than some of the most representative similarity search methods.