Collecting AI Conference Papers
The overall picture of the AI conference is as follows.
AI-related conference papers from AAAI, ISWC, ILP, RW, etc. were collected based on their proceedings.
General
This issue of the blog describes noteworthy technologies and their representative papers extracted from prominent international conferences. As criteria for selecting the technologies, those described in this blog, such as deep learning, reinforcement learning, probabilistic generative modeling, natural language processing, machine learning that can explain, and knowledge information processing, are referred to the respective linked articles, and the pickup of technologies other than those is done consciously.
AAAI
The Association for the Advancement of Artificial Intelligence (AAAI), one of the world’s top-tier conferences on artificial intelligence technology, has selected 30 outstanding papers for the AAAI Classic Paper. A Japanese translation is provided. The papers are not machine learning papers, which have been mainstream in recent years, and are worth reading to get new ideas to combine with them.
ISWC
A collection of papers from the first international Semantic Web conference. Many of the papers deal with the integration of Web services, which is the flexible processing of data after it has been connected. In detail, the research papers cover matching, retrieval, ontologies, RDF, etc., the position papers cover European implementations and steps to implement the Semantic Web, and the final system overview covers research papers on Semantic Web systems, enterprise applications, and using agents. The final system overview describes the Semantic Web systems in the research paper, enterprise applications, agent-based scheduling, visual analytics, etc. The table of contents is as follows. For example, in the poster session “Learning Organizational Memory”, the paper itself cannot be found on the Internet, but there are some knowledge management papers on handling organizational memory and personal memory inspired by it. However, there are many papers on knowledge management and human resource management related to organizational memory and individual memory.
Specific examples of organizational and individual knowledge management include the visualization of knowledge in an organization through cluster analysis using machine learning of text contents, and the combination of visualization of the number of repeats of text contents with word clouds. The approach of 20 years ago was to focus on structured data as text content, which was not dense enough to visualize the patterns extracted from the data, but not deep enough to visualize the knowledge. However, with the development of technology in recent years, it has become possible to approach organizational memory, which has been called “tacit knowledge” for a long time, by using voice recognition of information on conversations exchanged within an organization as unstructured data. By using voice recognition of conversations exchanged within an organization as data, it is possible to approach organizational memory, which has been called “tacit knowledge” for a long time, and it is becoming possible to add depth to the visualization of knowledge.
For example, it is now possible to visualize clustered knowledge domains using Zoomable Circle Packing, and to visualize the hierarchical structure of knowledge in an organization using tools such as Sequences Sunburst. For example, we can use Zoomable Circle Packing to visualize clustered knowledge domains, or we can use tools such as Sequences Sunburst to present the hierarchical structure of knowledge in an organization, or we can use tools such as Temporal Force-Directed Graph to visualize changes in the time series of relationships between people and contexts by focusing on information in conversations.
Similarly, various approaches are possible for recognizing patterns in data. The application of relational data learning methods such as spectral clustering, topic model approaches, and simulation methods such as Bayesian models make it possible to extract patterns in knowledge that were difficult to extract when only simple machine learning methods were available.
A collection of papers from the second International Semantic Web Conference. Compared to the first ISWC2002, the contents are much more diverse. In the basic part, OWL and RDFS are discussed for web integration, followed by ontology-based reasoning, Semantic Web services, which were discussed in the previous conference, data reliability and security, and agent systems for web service integration. This is followed by agent systems, information retrieval, and multimedia.
Finally, we move on to various tools and their applications and practical applications (Industrial Track). The industrial track covers knowledge portals in the enterprise, task computing, semantic annotation tools, and applications in the automotive and chemical industries. The table of contents is as follows.
A collection of papers from the 3rd International Semantic Web Conference. Compared to the previous ISWC2003, Data Semantics, such as thesaurus, context, bipartite graph as an intermediate data representation of RDF, etc. are discussed. In addition, P2P systems, user interfaces and visualization, and large-scale knowledge management are newly discussed.
In the deepening of the previous discussion, the application of Semantic Web services to the real world is discussed, such as the application to biotechnology and the automation of chemical experiments, and discussions on inference (related to OWL) and search (various approaches to search queries) are advanced, as well as middleware, data interoperability, and ontology maintenance.
In the final industrial track, business applications and the ontology platform at NASA are introduced. In the section on Semantic Web services, the application to bioinformatics, automation of chemical experiments using Semantic Grid, consideration of web service workflows, semi-automatic annotation, eScience, etc. are also discussed. The table of contents is as follows.
There are only three major tracks: the Research Track, the Industrial Track, and the Semantic Web Challenge. The Research Track discusses semantic search ranking, handling ontologies over time, multimedia support, encryption, dynamic community search using biographies, and probabilistic ontology mapping tools. The Industrial Track discusses legal knowledge management systems, applications in the medical field, how to develop requirements specifications for knowledge processing, applications in logistics, and applications in automotive systems.
Workshops include Modular Ontology, Ontology Matching, Semantic Web Policy, Semantic Authoring and Annotation, Healthcare and Life Sciences, Sensor Networks, Terra-Cognica Geospatial Semantic Web, Uncertain Reasoning Semantic Ewb (ERSW), and Content Mining with Natural Language Processing. Uncertain Reasoning Semantic Ewb (ERSW), and content mining with natural language processing.
Workshops being held include Terra-Cognica Geospatial Semantic Web in Ubiquitous Healthcare, Semantic Web, Uncertain Reasoning Semantic Ewb (ERSW), Privacy and Accountability, Finding Experts Using Semantic Web, Ontology Matching, Ontology Tools, Semantic Web in Buildings/Products/Engineering, Text to Knowledge, etc. Using the Semantic Web to Find Experts, Ontology Matching, Ontology Tools, Semantic Web in Buildings/Products/Engineering, Semantic Web Service Matchmaking, Text to Knowledge, etc.
Workshops being held include Social Data and the Semantic Web, Scalable Web-based Systems, Uncertain Reasoning Semantic Ewb (ERSW), Ontology Matching, Ontology Patterns, Ontology Supported Business Intelligence, Ontology Dynamics, and Semantic Web Service Matchmaking. supported business intelligence, ontology dynamics, Semantic Web service matchmaking, etc.
Workshops being held include: Structured Knowledge Sharing/Building, Ontology Matching, Ontology Patterns, Role of the Semantic Web in History Management, Service Matching in the Semantic Web, User Interaction, Social Data and the Semantic Web, scalable web-based systems, Uncertain Reasoning Semantic Ewb (ERSW), sensor networks, etc.
Workshops held include Uncertain Reasoning Semantic Ewb (ERSW), sensor networks, ontology matching, LOD (e-government), OWL2, semantic search, the role of the Semantic Web in history management, knowledge-based systems, service matching in the Semantic Web, social data and the Semantic Web, ontology patterns, etc. The role of the Semantic Web in knowledge base systems, service matching in the Semantic Web, social data and the Semantic Web, ontology patterns, etc.
In this article, I will describe the ISWC 2011 held in Bonn, Germany. The workshops include Terra-Cognica Geospatial Semantic Web, Uncertain Reasoning Semantic Ewb (ERSW) and Sensor Networks, Ontology Matching, Event Detection on the Semantic Web, Multilingual Semantic Web Multilingual Semantic Web, personalized information management, knowledge-based systems, ontology dynamics, LOD (science), web-scale knowledge extraction, etc.
This time, I would like to talk about ISWC2012 held in Boston, USA. This year’s ISWC 2012 continued the discussion on Uncertain Reasoning Semantic Ewb (ERSW), sensor networks, ontology matching, scalable systems for practical use, integration with cloud services, recommender systems, multilingual semantics, semantic web programming, etc. Semantics, Semantic Web programming, etc. are discussed.
In this article, I will describe ISWC2013, which was held in Sydney, Australia. The contents of the conference include Semantic Statistics, Stream Reasoning, Event Detection/Representation/Use in the Semantic Web, Linked Mosquito Furniture Experiment Support, Linked Data Ecosystem for Industry, Ontology Patterns, Sensor Networks, Ontology Matching Scalable Semantic Web, Crowdsourcing the Semantic Web, Linked Data for Information Extraction, Semantic Machine Learning for Agricultural and Environmental Informatics, Semantic Web Privacy and Policy, Semantic Web Enterprise, Semantic Music and Media, and more.
In this article, I will describe ISWC2014 held in Trentino, Italy. The contents include LOD, Context, Interpretation and Meaning as Natural Language Processing, Semantic Retrieval of Semantic Data, Applications in Education, LOD for Information Extraction, Linked Chemistry, On Data Reliability, Natural Language Interfaces, NLP and DBPedia, Ontology Matching, Time Transitions, Privacy privacy, ontology and semantic web patterns, scalable web-based knowledge systems, smart cities, semantic and other rare, semantic collaboration, social feb, semantic geographic information, reasoning about uncertainty, etc.
I will describe ISWC2015 held in Pennsylvania, USA. There were more presentations on datasets and performance, ontology and graphs, Linked Data, ODBA (Ontology Based Data Access), and Industry. Among the papers presented were one on a platform called LOD Laundromat, which unifies different LODs into a unified format, and another on ontology mapping (using a system called Karma) of information extracted from 68 million texts collected from the Web, and mapping the same entity of instructions to different entities. There was a report on a system that extracts information on human trafficking from various advertisements by mapping entities, ontology alignment that maps items defined separately in multiple ontologies, and a card-type search engine called knowledge Card.
ISWC was held at Kobe International Conference Center from October 17 to 21, 2016. The Resources Track invited oral presentations on resource sharing that contributes to the research community, including datasets, ontologies, services, benchmarks, ontology design patterns, workflows, methodologies, etc. The Applications Track invited presentations on applications, business cases, and prototypes that can be deployed in the real world. In the Applications Track, we are looking for applications, business cases, and prototypes that could be deployed in the real world. The session time was set for each theme, and oral presentations were given according to the theme regardless of the division. The themes ranged from Linked Data, Ontology, Inference, Query, Search, Natural Language Processing, Knowledge Graphs, Smart Planet, and many more.
Voila (Visualization and Interaction for Ontologies and Linked Data) has a ViziQuer as a UI for generating R2RML mappings,* Linked DataReactor, and various tree information Treevis.net, which classifies visualizations, is one such example.
There are also reports on learning multimodal relational knowledge using knowledge graphs that link semantic information such as textual information, image attribute information such as image information that is difficult to represent in text, and knowledge graphs that link these two types of information, and semantic data mining (SDM: background knowledge interconnected with annotated data). efficient method for generating rules that can be easily interpreted by end-users), or on improving visual relationship detection using semantic modeling of scene descriptions by StephanBrier, who used a background knowledge base to improve prediction of relationships between parts of an image. The event included the following.
FY 2018 is characterized in particular by Knowledge Graph-related and deep learning-related presentations.
First, regarding knowledge graphs, “Knowledge Graphs as enterprise assets,” Google’s knowledge graph has 1 billion objects and 70 billion assertions, while Facebook’s knowledge graph, unlike its social graph, has just increased this year and has 5 There are 10 million entities and 500 million assertions. More importantly, these are important assets for the application. For example, KG is central to the creation of product pages at eBay, KG is key to entity search and assistants at Google and Microsoft, and IBM uses it as part of their enterprise products.
And as for deep learning as a technique, it is part of the Semantic Web Researcher’s Toolbox. Notable papers at DNN include.
ISWC2019 was held in Auckland (New Zealand), and similar to the previous ISWC2018, there were many reports on knowledge (graph) data and their application to Q&A systems, etc.
One report of note was “Logical Semantics Approach for Data Modeling in XBRL Taxonomies” (the technical area of XBRL includes financial reporting, natural He mentioned that the future contribution of XBRL to semantic technology lies in the utilization of large-scale data (including AI) in these technical areas. based geospatial data integration and visualization with Semantic Web technologies A report on the implementation of geovisualization. The report states that the demand for Spatial Data Infrastructure (SDI) has been increasing in Europe and the U.S. in recent years, and that SDI can contribute as a methodology for handling ontologies in geospatial space). The report “How to make latent factors interpretable by feeding Factorization machines with knowledge graphs” (Hybrid Factorization Machine (kaHFM) demonstration. (Referring to the validation of a method for initializing latent factors for the Factorization Machine using a knowledge graph to train interpretable models), “Summarizing News Articles using Question-and-Answer Pairs via Learning” (Google research presentation on the use of semantic technology in Q&A systems. The system mines questions from data associated with news stories and learns questions directly from the story content. This is the first demonstration of a learning-based approach to generating structured summaries of news stories with question-answer pairs to capture important and interesting aspects of a news story. The validation data is from the SQuAD dataset 2). and “Using a Knowledge Graph of Scenes to Enable the Search of Autonomous DrivingData” (describes a demonstration at Bosch using semantic technology. The intended use of the data is to provide large-scale data for automated driving technology. Benefits include improved capability to represent, integrate, and query automated driving data. It is also anticipated that data scientists and engineers within various projects and departments will be able to reuse data from each other’s applications), “Using Event Graph to Improve Question Answering in E-commerce Customer Service” (describing AliMe, an intelligent assistant that provides a question-and-answer service, which can answer more than 90% of the millions of questions per day. This session proposes an Event Graph that provides a reasoning mechanism to obtain accurate answers to the question types “why”, “wherefore”, “what if”, and “how next”. Events are properties of choices of situations that can happen, and the baseline knowledge graph is generated using WIKIDATA, DBpedia, YAGO, etc.), “Querying Enterprise Knowledge Graph With Natural Language” (describes research on interactive interfaces to large enterprise knowledge graphs. He calls this mechanism Yugen (a deep learning-based interactive AI that answers user questions). Yugen is voice-based, so it has the advantage of reducing the cost of learning a specific query language), “Product Classification Using Microdata Annotations” (which described the task of automatically classifying products into universal categories using markup data published on the Web (in this case, RDF and Microdata). The challenge would be to handle the information needed for classification (e.g., treatment of individual websites, consistency across websites, site-specific product labels, etc.). This will be an example of using RDF as input data for deep learning), “Difficulty-controllable Multi-hop Question Generation From Knowledge Graphs” ( He described neural network-based multi-hop questions. A multi-hop question is a question that can only be answered by hopping a node in the graph structure two or more times. As a solution, he mentioned that he had implemented an encoder-decoder model conditional on the difficulty level and was able to generate complex questions via a large knowledge graph. However, it was difficult to achieve and seemed to require future research), “QaldGen: Towards Microbenchmarking of Question Answering Systems Over Knowledge Graphs” ( He mentioned that micro-benchmarking is necessary when trying to test domain-specific Q&A systems because of the time and effort required to generate questions. QaldGen was proposed as a framework for generating questions useful for micro-benchmarking), etc. Translated with www.DeepL.com/Translator (free version)
The ISWC2020 had a greatly enhanced presentation on the knowledge graph. The content was a Hybrid Knowledge Graph Ecosystem, an approach that uses ontologies to improve neural models and neural models to improve ontologies. The limitations that the Hybrid KG wants to overcome will be the challenges caused by the bias of the data that machine learning has and the challenges caused by the exceptions of local data, even if only in the knowledge representation. These would not only automate linking using ML, but would also leverage inference using KR to answer questions about the “why” of a phenomenon. Specific approaches include those that compute the transitive closure of a graph and then compute the node embedding of compound similarity, or even use GPT-3 for biomedical text, or daisy-chain BERT, LSTM, and CRF for NER and linkage.
Or as Semantic Web programming, primarily describing how knowledge graphs support and enhance developers and bring intelligence to various coding activities.
I will discuss ISWC2021, which was held as a virtual conference due to the coronavirus. As in previous years, many presentations related to knowledge graphs were made at this year’s conference.
As in previous years, a wide variety of papers were submitted in this year’s Research Track, with contributions falling into four categories. First, papers on classical reasoning and query answering for ontologies of various shapes, such as RDF(S)/OWL, SHACL, SPARQL, and their variants and extensions, as well as non-standard tasks such as repair, description, and database mapping. Also, as in previous years, papers on ontology/knowledge graph embedding, especially graph neural networks of various forms and their applications such as zero/few-shot learning, image/object classification, and various NLP tasks. There is also a category of papers focused on specific knowledge graph tasks, such as link and type prediction, entity alignment, etc. Finally, there were reports on surveys of the current state of the art, including the availability of LOD and structural patterns in ontologies.
Inductive Logic Programming
The 18th International Conference on Inductive Logic Programming was held in Prague, September 10-12, 2008, and while the ILP community clearly continues to cherish its beloved framework of first-order logical representations, the research presented at ILP2008 showed that there is still room for both extensions to established ILP approaches, and the exploration of new logical induction frameworks such as Brave Induction, show that there is still room for both extensions of these approaches, and further into the areas of statistical relational learning, graph mining, the Semantic Web, bioinformatics, and cognitive science.
For almost two decades, the ILP conference series has been the premier forum for research on logic-based approaches to machine learning, and the 19th International Conference on Inductive Logic Programming, held July 2-4, 2009, in Leuven, continues this tradition. SRL-2009 – International Workshop on Statistical Relational Learning, MLG-2009 – 7th International Workshop on Mining and Learning with Graphs, making it a conference open to the rest of the community. Each of these three events has its own focus, emphasis, and traditions, but fundamentally they share the problem of learning about structured data in the form of graphs, relational descriptions, and logic as a subject of study. Thus, the events were held concurrently to promote greater interaction among the three communities.
In this issue, we discuss revised papers from the 20th International Conference on Inductive Logic Programming (ILP2010), held in Florence, Italy, June 27-30, 2010.
The ILP conference series began in 1991 and is a major international event on logic-based approaches to machine learning. In recent years, the scope of research has expanded significantly, with the integration of statistical learning and other probabilistic approaches being explored.
ILP2011 was held at Cumberland Lodge in the UK from July 31 to August 3, 2011, under the auspices of the Department of Computing at Imperial College London.
The 31 proceedings papers represent the diversity and vitality of current ILP research, including ILP theory, implementation, probabilistic ILP, biological applications, subgroup discovery, grammatical inference, relational kernels, Petri net learning, spatial learning, graph-based learning, and learning behavioral models.
Describes the 22nd International Conference on Inductive Logic Programming, ILP 2012, held in Dubrovnik on September 17-19, 2012 The ILP conference series began in 1991 and is the leading international forum on learning from structured data. Initially focused on induction in logic programming, it has expanded its scope in recent years and has attracted a great deal of attention and interest. It now focuses on all aspects of learning from structured data, including logic learning, multi-branch relational learning, data mining, statistical relational learning, graph and tree structure mining, and relational reinforcement learning.
The papers in ILP2012 provide a good representation of the breadth of current ILP research, including propositionalization, logical foundations, implementation, probabilistic ILP, applications to robotics and biology, grammatical inference, spatial learning, and graph-based learning.
ILP 2016 took place at the Warren House Conference Centre in London from September 4-6, 2016.Since its first edition in 1991, the annual ILP conference has been the premier international forum for learning from structured relational data It has been functioning. Initially focused on induction in logic programs, over the years it has greatly expanded its research horizons to include learning in logic, multi-relational data mining, statistical relational learning, graph and tree mining, learning in other (non-propositional) logic-based knowledge representation frameworks, exploring the intersection with statistical learning, other probabilistic He has made contributions on all aspects of the approach and others. Theoretical advances in these areas have also been accompanied by challenging applications of these techniques to important problems in areas such as bioinformatics, medicine, and text mining.
We describe the 27th International Conference on Inductive Logic Programming, ILP2017, held in Orléans, France, in September 2017. Contents include robot control, knowledge bases and medicine, statistical machine learning in image recognition, relational learning, logic-based event recognition systems, the problem of learning Boltzmann machine classifiers from relational data, parallel inductive logic programming, learning from interpretative transitions (LFIT), Lifted Relational Neural Networks (LRNN), and improvements to WOrd2Vec will be described.
Inductive logic programming (ILP) is a subfield of machine learning that relies on logic programming as a unified expression language for representing examples, background knowledge, and hypotheses. With its powerful expressive form based on first-order predicate logic, ILP provides an excellent vehicle for multi-relational learning and data mining.
The ILP conference series, initiated in 1991, will be the premier international forum for learning from structured or semi-structured relational data. Originally focused on the introduction of logic programs, over the years the scope of research has expanded significantly to include logic, multi-relational data mining, statistical relational learning, graph and tree mining, other learning (non – proposed) logic-based knowledge representation frameworks, statistical learning and other probabilistic Research into approaches has been reported.
In this issue, we describe the 29th International Conference on Inductive Logic Programming, held in Plovdiv, Bulgaria, September 3-5, 2019.
Inductive logic programming (ILP) is a subfield of machine learning that relies on logic programming as a unified representation language for expressing examples, background knowledge, and hypotheses. With its powerful expressive form based on first-order predicate logic, ILP provides an excellent means for multi-relational learning and data mining.
The ILP conference series, initiated in 1991, provides the premier international forum for learning from structured or semi-structured relational data. Originally focused on introducing logic programs, over the years the scope of research has expanded significantly to include logic, multi-relational data mining, statistical relational learning, graph and tree mining, other learning (non – proposed) logic-based knowledge representation frameworks, statistical learning and other probabilistic approaches and their intersections are being investigated.
In this issue, we discuss ILP2021, which was skipped a year due to the coronal pandemic. Inductive logic programming (ILP) is a branch of machine learning that focuses on learning logical representations from relational data. the ILP conference series was started in 1991 and is the leading international forum on learning from structured or semi-structured relational data, multi-relational learning and data mining. international forum on learning from structured or semi-structured relational data, multi-relational learning, and data mining. Initially focused on induction of logic programs, over the years the scope of research has broadened considerably to include all aspects of logic learning, statistical relational learning, graph and tree mining, learning other (non-propositional) logic-based knowledge representation frameworks, and exploring the intersection of statistical learning and other probabilistic approaches. The research will.
Reasoning Web
This issue contains tutorial papers from the summer school “Reasoning Web” (http://reasoningweb.org), held July 25-29, 2005. The purpose of the school will be to introduce the methods and issues of the Semantic Web, a major current attempt at Web research in which the World Wide Web Consortium W3C plays an important role.
The main idea of the Semantic Web is to enrich Web data with metadata that conveys the “meaning” of the data and allows Web-based systems to reason about the data (and metadata). Metadata used in Semantic Web applications is usually linked to concepts in the application domain that are shared by different applications. Such a conceptualization is called an ontology and specifies classes of objects and the relationships between them. Ontologies are defined by ontology languages that are based on logic and support formal reasoning. Just as the current Web is inherently heterogeneous in its data format and data semantics, the Semantic Web is inherently heterogeneous in its form of reasoning. In other words, a single form of reasoning has proven to be insufficient for the Semantic Web. For example, while ontological reasoning in general relies on monotonic negation, databases, web databases, and web-based information systems require non-monotonic reasoning. Constraint reasoning is needed to deal with time (because time intervals are dealt with). Topology-based reasoning, e.g., mobile computing applications, requires programming. On the other hand, (forward and backward) chaining is reasoning that deals with views, such as databases (because views, i.e., virtual data, can be derived from real data by operations such as merging and projection).
In this article, we describe the summer school “Reasoning Web 2006” (http://reasoningweb.org), organized by the Universidade Nova de Lisboa (New University of Lisbon), which was held in Lisbon from September 4 to 6, 2006. Reasoning is one of the central issues in the research and development of the Semantic Web. Indeed, the Semantic Web aims to enhance today’s Web with “metadata” carrying semantics and reasoning methods. The Semantic Web is a very active area of research and development involving both academia and industry.
The program of the Summer School “Reasoning Web 2006” will address the following issues. (1) Semantic Web query languages, (2) Semantic Web rules and ontologies, and (3) Bioinformatics and medical ontologies – industrial aspects.
Reasoning Web will be a summer school series focusing on theoretical foundations, state-of-the-art approaches, and practical solutions for reasoning in the Web of Semantics. This issue will be the tutorial notes from the Reasoning Web summer school 2007, held in Dresden, Germany, in September 2007.
The first part of the 2007 edition, “Fundamentals of Reasoning and Reasoning Languages,” surveys the concepts and methods of rule-based query languages. It also provides a comprehensive introduction to description logics and their use. The second part, “Rules and Policies,” deals with reactive rules and rule-based policy representation; the importance and promising solutions for rule exchange on the Web are discussed, along with an overview of current W3C efforts. A thorough discussion is provided. Part 3, “Applications of Semantic Web Reasoning,” presents practical uses of Semantic Web reasoning. The academic perspective is presented by contributions on reasoning in semantic wikis. The industrial perspective is presented by contributions on the importance of semantic technologies in enterprise search solutions, building an enterprise knowledge base with semantic wiki representation, and discovering and selecting semantic web services in B2B scenarios.
The Reasoning Web Summer School is a well-established event attended by academic and industrial professionals and doctoral students interested in fundamental and applied aspects of the Semantic Web. This issue contains the lecture transcripts of the 4th Summer School, held in Venice, Italy, in September 2008. The first three chapters cover (1) languages, formats, and standards employed to encode semantic information, (2) “soft” extensions useful in contexts such as multimedia and social network applications, and (3) controlled natural language techniques to bring ontology authoring closer to the end user and introductory content, while the remaining chapters cover key application areas are covered.
The Semantic Web is one of the major current endeavors in applied computer science. The goal of the Semantic Web is to enhance the existing Web with metadata and processing methods to provide advanced (so-called intelligent) capabilities to Web-based systems, especially context awareness and decision support.
The advanced capabilities required in Semantic Web application scenarios primarily require reasoning. Reasoning capabilities are provided by the Semantic Web languages currently under development. However, many of these languages have been developed from a function-centric (e.g., ontology reasoning, access validation) or application-centric (e.g., Web service search, composition) perspective. For Semantic Web systems and applications, a reasoning technology-centric perspective that complements the above activities is desirable.
This issue of Reasoning Web is a series of summer schools on theoretical foundations, modern approaches, and practical solutions for reasoning in the Web of Semantics. This book is the tutorial note of the 6th school held from August 30 to September 3, 2010.
This year’s focus is on the application of semantic technology to software engineering and suitable reasoning techniques. The application of semantic technology in software engineering is not so easy, and several challenges must be solved in order to apply reasoning to software modeling.
In this issue, we describe the 7th Reasoning Web Summer School 2011, held in Galway, Ireland, August 23-27, 2011 The Reasoning Web Summer School is an established event in the field of applications of reasoning techniques on the Web and attracts young researchers to this new field, targeting scientific discussions of existing researchers.
The 2011 Summer School featured 12 lectures, focusing on the application of reasoning to the “Web of Data”. The first four chapters covered the principles of Resource Description Framework (RDF) and Linked Data (Chapter 1), the description logic underlying the Web Ontology Language (OWL) (Chapter 2), the use of the query language SPARQL with OWL (Chapter 3), efficient and database infrastructure related to scalable RDF processing (Chapter 4), followed by an approach to scalable OWL reasoning on Linked Data in Chapter 5, rules and logic programming techniques related to Web reasoning in the following Chapter 6, and in Chapter 7, a combination of rule-based reasoning and OWL in particular. combination of rule-based reasoning and OWL is described in Chapter 7.
The Reasoning Web Summer School series has become a major educational event in the active field of reasoning on the Web, attracting both young and experienced researchers. The Reasoning Web Summer School series has become a major educational event in the active field of reasoning on the Web, attracting young and seasoned researchers alike.
The 2012 Summer School program was organized around the general motif of “Advanced Query Response on the Web. It also focused on application areas related to the Semantic Web where query response plays an important role and where, by its nature, query response poses new challenges and problems.
In this issue, we describe the 9th Reasoning Web Summer School 2013, held in Mannheim, Germany, from July 30 to August 2, 2013.
The 2013 Summer School covered various aspects of web reasoning, from extensible and lightweight formats such as RDF to more expressive logic languages based on description logic, as well as basic reasoning used in answer set programming and ontology-based data access techniques, and emerging topics such as geospatial information handling and inference-driven information extraction and integration are also covered.
In this issue, we describe the 10th Reasoning Web Sum- mer School (RW 2014), held in Athens, Greece, from September 8-13, 2014.
The theme of the conference will be “Reasoning on the Web in the Age of Big Data.” The invention of new technologies such as sensors, social networking platforms, and smartphones has enabled organizations to tap into vast amounts of previously unavailable data and combine it with their own internal proprietary data. At the same time, significant progress has been made in fundamental technologies (e.g., elastic cloud computing infrastructure) that enable data management and knowledge discovery technologies that handle terabytes and petabytes of data. Reflecting this industrial reality, the report introduces recent advances in aspects of big data such as the Semantic Web and Linked Data, as well as the fundamentals of inference techniques for tackling big data applications.
This article describes the tutorial papers prepared for the 11th Reasoning Web Summer School (RW 2015) held in Berlin, Germany, from July 31 to August 4, 2015.The 2015 edition of the School was hosted by the Free University of Berlin, Germany, Computer Science The theme for 2015 is “Web Logic Rules” (findings on the Semantic Web, Linked Data, ontologies, rules, and logic).
In this issue, we describe the 12th Reasoning Web Summer School (RW2016) held in Aberdeen, UK, from September 5 to 9, 2016. The content covered knowledge graphs, linked data, semantics, fuzzy RDF, and logical foundations for building and querying OWL knowledge bases.
In this issue, we describe the 13th Reasoning Web, held in London, UK, in July 2017. The theme of this year’s conference was “Semantic Interoperability on the Web” and encompassed themes such as data integration, open data management, reasoning on linked data, mapping databases and ontologies, query answering on ontologies, hybrid reasoning with rules and ontologies, and dynamic ontology-based systems. This issue also focuses on these topics, as well as basic techniques of reasoning used in answer set programming and ontologies.
In this issue, we describe the 14th Reasoning Web, held in Esch-sur-Alzette, Luxembourg, in September 2018. Specifically, we will discuss normative reasoning, a quick survey on efficient search combining text corpora and knowledge bases, large-scale probabilistic knowledge bases, the application of Conditional Random Fields (CRAFs) to knowledge base generation tasks, the use of DBpedia and large cross-domain knowledge graphs such as Wikidata, automatic construction of large knowledge graphs (KGs) and learning rules from knowledge graphs, processing large RDF graphs, developing stream processing applications in a web environment, and reasoning about very large knowledge bases.
In this issue, we describe the 15th Reasoning Web, held in Bolzano, Italy, in September 2019. The topic will be Explainable AI, with a detailed description and analysis of the main reasoning and explanation methods for ontologies using description logic: tableau procedures and axiom pinpointing algorithms, semantic query responses to knowledge bases, data provenancing, entity-centric knowledge base applications, formal concept analysis, an approach to explaining data by lattice theory, learning interpretable models from data, logical problems such as proposition satisfiability, discrete problems such as constraint satisfaction, and learning full-scale mathematical optimization tasks, distributed computing systems, and explainable AI planning will be described.
This issue of Reasoning Web is dedicated to the 16th Reasoning Web, which will be held virtually in June 2020 due to Corona’s influence. The main theme will be “Declarative Artificial Intelligence”. Specifically, I will give an overview of high-level research directions and open problems related to lightweight description logic (DL) ontology explainable AI (XAI), stream inference, solution set programming (ASP), limit datalogs (a recent declarative query language for data analysis), and knowledge graphs. An overview will be given.
In this issue, we describe the 17th Reasoning Web held in Leuven, Belgium in 20219. Specifically, I will discuss fundamentals on querying graph-structured data, reasoning with ontology languages based on description logics and non-monotonic rule languages, combining symbolic reasoning and deep learning, the Semantic Web and knowledge graphs and machine learning, building information modeling (BIM), the Geospatially Linked Open Data, Ontology Evaluation Techniques, Planning Agents, Cloud-based Electronic Health Record (EHR) Systems, COVID Pandemic Management, Belief Revision and its application to Description Logic and Ontology Repair, Temporal Equilibrium Logic (TEL) and its solution Set Programming (ASP), an introduction and review of Shapes Constraint Language (SHACL), a W3C recommended language for RDF data validation, and score-based Explanations will be presented.
Advances in Artificial Intelligence
In this article, we describe the 36th German Conference on Artificial Intelligence (KI 2013), held at the University of Koblenz, Germany, from September 16-20, 2013.Started in 1975 by the German Workshop on AI (GWAI), the German Conference on Artificial Intelligence is the leading forum for artificial intelligence research in Germany and is attended by many international guests.
The papers in detail range from agents, robotics, cognitive science, machine learning, swarm intelligence, planning, knowledge modeling, reasoning, and ontology.
This issue was held in Stuttgart, Germany, September 22-26, 2014. We describe the 37th German Conference on Artificial Intelligence (KI 2014). This conference will be the most important forum in Germany where academic and industry researchers from all areas of artificial intelligence will gather to exchange the latest information and research results on the theory and application of intelligent systems technology.
At KI 2014, Wolfram Burgard (University of Freiburg, Germany) will give an overview of probabilistic techniques for mobile robot navigation, Hans van Ditmarsch (LORIA Nancy, France) will give a talk on dynamic cognitive logic and artificial Intelligence by Hans van Ditmarsch (LORIA Nancy, France), and a keynote lecture on Allocation in Practice by oby Walsh (NICTA and UNSW Sydney, Australia).
The 8th Workshop on Emotion and Computing – Current Research and Future Impact, the 28th Workshop on Planen/Scheduling und Kon- figurieren/Entwerfen (PuK), and the Higher Level Workshop on Cognition and Computation were also held. Workshops on Cognition and Computation were held, plus tutorials on Probabilistic Programming (Angelika Kimmig, KU Leuven) and Human Computation (Fran ̧ Bry, LMU Munich).
Other main topics included Cognitive Modeling, Computer Vision, Constraint Satisfaction, Search, and Optimization, Knowledge Representation and Reasoning, Machine Learning and Data Mining, and Planning. Machine Learning and Data Mining, and Planning and Scheduling.
This report describes the proceedings of the 38th German Conference on Artificial Intelligence, KI 2015, held in Dresden, Germany, September 21-25, 2015. The conference was preceded by an international summer school on reasoning organized by the International Center for Computational Logic.
At KI 2015, we were able to secure the participation of three distinguished scientists as keynote speakers: Molham Aref (LogicBlox, USA) on declarative probabilistic programming, Ross D. King (University of Manchester) on working with robot scientists work, and Francesca Rossi (University of Padova) spoke on safety and ethical issues in systems for collective decision making.
We describe the 39th German Conference on Artificial Intelligence, KI 2016, held September 26-30, 2016 This annual conference, which began in 1975 as the German Workshop on AI (GWAI), traditionally brings together academic and industrial researchers in all areas of AI to provide an and algorithms, and serves as an international forum for research on fundamentals and applications. This year’s conference was held jointly with the Austrian Society for Artificial Intelligence (ÖGAI) in Klagenfurt, Austria.
We describe the 40th German Conference on Artificial Intelligence, KI 2017, which took place at the Technical University of Dortmund from September 25-29, 2017. The presentations covered a wide range of topics such as agents, robotics, cognitive science, machine learning, planning, knowledge representation, reasoning, ontology, as well as social media, psychology, and transportation systems.
In this issue, we discuss papers presented at KI2018, held in Berlin from September 24-28, 2018. Prominent research topics at this year’s conference will be machine learning, multi-agent systems, and belief revision. Overall, KI 2018 provided a broad overview of current research topics in AI.
This issue describes the 42nd German Conference on Artificial Intelligence (KI 2019), held in Kassel, Germany, from September 23-26, 2019.KI 2019 has a special focus on “AI methods for Argumentation” and is particularly interested in the use of methods from all areas of AI to Submissions were invited to understand, formalize, and generate argumentation structures in natural language. This special focus theme was organized in cooperation with the DFG-funded priority program RATIO (Robust Argumentation Machines; Robust Argumentation Machines).
- KI2020: Advances in Artificial Intelligence Papers
- KI2021: Advances in Artificial Intelligence Papers
Uncertain Reasoning
This book contains the proceedings of the first three workshops on Uncertainty Reasoning for the Semantic Web (URSW) held at ISWC in 2005, 2006, and 2007. The papers presented here include revised and significantly expanded versions of papers presented at the workshops, as well as invited papers by leading experts in the field and related areas.
This book is the first comprehensive compilation of state-of-the-art research approaches to uncertainty reasoning in the context of the Semantic Web, capturing different models of uncertainty and approaches to deductive and inductive reasoning with uncertain formal knowledge.
This is the second volume on “Uncertainty Reasoning for the Semantic Web” and is the result of the Uncertainty Reasoning for the Semantic Web (URSW) workshops held at the International Semantic Web Conference (ISWC) in 2008, 2009, and 2010. It is a revised and significantly extended version of the paths presented at the workshops on Uncertainty Reasoning for the Semantic Web (URSW) at the International Semantic Web Conference (ISWC) in 2008, 2009, and 2010, and at the First International Workshop on Un- certainty in Description Logics (UniDL) in 2010. This is a revised and significantly expanded version of the paths presented at the 2010 First International Workshop on Un- certainty in Description Logics (UniDL).
The two volumes provide a comprehensive compilation of state-of-the-art research approaches to uncertainty reasoning in the context of the Semantic Web, capturing different models of uncertainty and approaches to inductive reasoning as well as inductive reasoning with uncertain formal knowledge.
- From the Uncertainty Reasoning for the Semantic Web 3 Proceedings
In this issue, we discuss Volume 3 of Uncertainty Reasoning for the Semantic Web. This time, we categorize the approaches to those uncertainties as follows. (1) Probabilistic and Dempster-Shafer models, (2) Fuzzy and possibility models, (3) Inductive reasoning and machine learning, and (4) Hybrid approaches.
Knowledge Graph Related Papers
In this issue, we discuss papers presented at CCKS 2018: China Conference on Knowledge Graph and Semantic Computing, held in Tianjin, China, August 14-17, 2018 CCKS is the China Information Processing Society’s (CIPS) Conference on Language and CCKS covers a wide range of research areas including knowledge graphs, semantic web, linked data, NLP, knowledge representation, graph databases, etc., and is the leading forum on knowledge graphs and semantic technologies.
The development of effective techniques for knowledge representation and reasoning (KRR) is an important aspect of successful intelligent systems. Various representation paradigms, as well as reasoning systems using these paradigms, have been extensively studied. However, new challenges, problems, and issues have emerged in knowledge representation in artificial intelligence (AI), such as the logical manipulation of increasingly large information sets (see, for example, the Semantic Web and bioinformatics). In addition, improvements in storage capacity and computational performance have affected the nature of KRR systems, shifting the focus to expressive power and execution performance. As a result, KRR research faces the challenge of developing knowledge representation structures that are optimal for large-scale inference. This new generation of KRR systems includes graph-based knowledge representation formalisms such as constraint networks (CN), Bayesian networks (BN), semantic networks (SN), concept graphs (CG), formal concept analysis (FCA), CP-net, GAI-net, argumentation frameworks The purpose of the Graph Structures for Knowledge Representation and Reasoning (GKR) workshop series is to bring together researchers involved in the development and application of graph-based knowledge representation formalisms and reasoning techniques. The goal of the Graph Structures for Knowledge Representation and Reasoning (GKR) workshop series is to bring together researchers involved in the development and application of graph-based knowledge representation formats and reasoning techniques.
Data analysis applies algorithmic processes to derive insights. It is now used in many industries to help organizations and companies make better decisions and to validate or disprove existing theories and models. The term data analytics is often used interchangeably with intelligence, statistics, inference, data mining, and knowledge discovery. In the era of big data, big data analytics refers to strategies for analyzing large amounts of data collected from a variety of sources, including social networks, transaction records, video, digital images, and various sensors. This book aims to introduce some of the definitions, methods, tools, frameworks, and solutions for big data processing, starting from information extraction and knowledge representation, through knowledge processing, analysis, visualization, sense-making, and practical applications.
However, this book is not intended to cover all the methods of big data analysis, nor is it intended to be an exhaustive bibliography. The chapters in this book address the appropriate aspects of the data processing chain, with particular emphasis on understanding enterprise knowledge graphs, semantic big data architectures, and smart data analytics solutions.
Other AI Papers and Proceedings
- Proceedings of Genetic Programming Theory and Practice XWhat we describe here will be the 10th Workshop on Genetic Programming, Theory and Practice, held May 12-14, 2012, at the Center for Complex Systems Research at the University of Michigan in Ann Arbor. The goal of this workshop series will be to facilitate the exchange of research results and ideas between those who focus on the theory of genetic programming (GP) and those who focus on the application of GP to a variety of real-world problems. Additional information about the workshop, addenda to the chapters, and a site for ongoing discussions by participants and others can be found at http://cscs.umich.edu/gptp-workshops/.
コメント