Search

Best Paper Award ​© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., The Web has a collection of over 150 million tables, which as a whole represents an invaluable source of semi-structured knowledge. Such tables are commonly referred to as Web tables, and are considerably easier to leverage in automated processes than completely unstructured, free-format text. Understanding the semantics of Web tables is important since they are used in various applications like knowledge base augmentation, information retrieval or natural language interfaces for databases. The task of understanding the semantics of a given Web table is known as Web table annotation. In recent years, it has been tackled through methods where the table is enriched using existing knowledge bases containing valuable information on the domain at hand, its entities and their mutual relationships. In this paper, we present two novel and unsupervised Web table annotation methods, which leverage the context of the tables to better capture their semantics. Our first method is lookup-based and exploits text similarity to find reference entities in the knowledge base. The second method uses distributional vector representations – a.k.a. embeddings – of the Web tables to elicit their context and disambiguate their semantics. Experiments show that our proposed approach outperforms the state of the art in Web table annotation by up to 18%. Another contribution of this work is a manually corrected version of one of the popular gold standard datasets, Limaye, with annotations from DBpedia. Our dataset and code are publicly available.

Best Paper Award ​© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., The Web has a collection of over 150 million tables, which as a whole represents an invaluable source of semi-structured knowledge. Such tables are commonly referred to as Web tables, and are considerably easier to leverage in automated processes than completely unstructured, free-format text. Understanding the semantics of Web tables is important since they are used in various applications like knowledge base augmentation, information retrieval or natural language interfaces for databases. The task of understanding the semantics of a given Web table is known as Web table annotation. In recent years, it has been tackled through methods where the table is enriched using existing knowledge bases containing valuable information on the domain at hand, its entities and their mutual relationships. In this paper, we present two novel and unsupervised Web table annotation methods, which leverage the context of the tables to better capture their semantics. Our first method is lookup-based and exploits text similarity to find reference entities in the knowledge base. The second method uses distributional vector representations – a.k.a. embeddings – of the Web tables to elicit their context and disambiguate their semantics. Experiments show that our proposed approach outperforms the state of the art in Web table annotation by up to 18%. Another contribution of this work is a manually corrected version of one of the popular gold standard datasets, Limaye, with annotations from DBpedia. Our dataset and code are publicly available.

Data resources are crucial to develop and maintain digital twins, which are seen as one of the key technologies within the paradigm shift called servitization in which organizations move from producing goods to offering services. Our hypothesis is that a large part of this data resources are already generated during the beginning of life (BOL) phases of the product lifecycle, but are not used in the middle of life (MOL) phases. This paper describes a framework and outlines a methodology to research the use of data resources from BOL phases in MOL phases. Projected results are an ontology of product data resources and an enhanced understanding of their usage in creating and maintaining digital twins.

This conceptual paper addresses the implementation of digital twins to provide decision support services in manufacturing environments. It differentiates the twin among different layers and phases of the equipment lifecycle and integrates different modelling techniques into a systematic decision chain.

Data resources are crucial to develop and maintain digital twins, which are seen as one of the key technologies within the paradigm shift called servitization in which organizations move from producing goods to offering services. Our hypothesis is that a large part of this data resources are already generated during the beginning of life (BOL) phases of the product lifecycle, but are not used in the middle of life (MOL) phases. This paper describes a framework and outlines a methodology to research the use of data resources from BOL phases in MOL phases. Projected results are an ontology of product data resources and an enhanced understanding of their usage in creating and maintaining digital twins.

This conceptual paper addresses the implementation of digital twins to provide decision support services in manufacturing environments. It differentiates the twin among different layers and phases of the equipment lifecycle and integrates different modelling techniques into a systematic decision chain.

We present preliminary results from our sixth placed entry to the Flatland international competition for train rescheduling, including two improvements for optimized reinforcement learning (RL) training efficiency, and two hypotheses with respect to the prospect of deep RL for complex real-world control tasks: first, that current state of the art policy gradient methods seem inappropriate in the domain of high-consequence environments; second, that learning explicit communication actions (an emerging machine-to-machine language, so to speak) might offer a remedy. These hypotheses need to be confirmed by future work. If confirmed, they hold promises with respect to optimizing highly efficient logistics ecosystems like the Swiss Federal Railways railway network.

We present preliminary results from our sixth placed entry to the Flatland international competition for train rescheduling, including two improvements for optimized reinforcement learning (RL) training efficiency, and two hypotheses with respect to the prospect of deep RL for complex real-world control tasks: first, that current state of the art policy gradient methods seem inappropriate in the domain of high-consequence environments; second, that learning explicit communication actions (an emerging machine-to-machine language, so to speak) might offer a remedy. These hypotheses need to be confirmed by future work. If confirmed, they hold promises with respect to optimizing highly efficient logistics ecosystems like the Swiss Federal Railways railway network.