A lot has happened lately and it’s about time I report on it. I know you just waited for it 🙂
In March and April I was very busy with in an EU STREP proposal that, if accepted, will be a great playground for my explanation research. The proposal answers to ICT Call 6 and is led by Anders Kofod-Petersen, SINTEF, Norway. Its title: „PERSOLVO: Enhanced human-robot interaction through explanations and adaptation“. It addresses objective „2.1 Cognitive systems, interaction, robotics“. Here’s the proposal abstract:
The long-term vision of service robotics is to be able to produce robots that interact in an intelligent way with their environment, and adapt their behaviour to match the evolving expectations of their users. PERSOLVO makes it technically feasible and economically viable to achieve enhanced interaction capabilities in service robots, through the use of explanations and adaptation techniques.
For service robot developers, PERSOLVO provides the means to conceive, design, implement and deploy innovative service robots. PERSOLVO-based robots are able to generate explanations on their decisions understandable by users, gather input from the user, adapt internal decision-making processes accordingly, and thus optimise future behaviours.
For service robot users, PERSOLVO leads to increased acceptance of robots in everyday situations as the ability of robots to explain their behaviour (especially in situations where behaviour was not quite as expected/desired) leads to greater trust. PERSOLVO enables users to influence the future behaviour of robots, through interactions based on explanations, and without the need to involve technicians.
PERSOLVO achieves this by:
• providing the theoretical foundations for developing explanation-aware robots,
• producing re-usable software components and engineering tools allowing companies to incorporate explanation-aware techniques in their service robot development,
• carrying out realistic experiments on the use of explanation-aware techniques in the context of three proof-of-concept applications to encourage widespread adoption.
In co-operation with robotics networks such as EURON and EUROP, the community of researchers and industrial developers interested in explanation-aware techniques will be expanded to relevant stake- holders in robotics. Potential partners will be addressed through industry workshops, summer schools, trade fair presentations and publications.
Anders and I are very happy about the high-quality partners for this endeavour, old and new, such as the Norwegian University of Science and Technology, Aldebaran Robotics (France), Entertainment Robotics (Denmark), and Fraunhofer IPA (Germany).
What else is worth reporting …
In April my term as chair of DFKI’s works council (‚Vorsitzender des Betriebsrats‘) ended. I was re-elected as works council member, but I did not offer myself as a candidate for the chair again. It was an interesting position, but I am a scientist at heart.
I have become a member of the management board of the special interest group Knowledge Management (Fachgruppe Wissensmanagement, in short FGWM), which addresses computer science methods for capturing, development, utilisation, and maintenance of knowledge for organisations and networks of people. The focus is on scientific foundations and practical applications. I am responsible for the group’s mailing list. So send me calls for papers etc. for distribution through the list (see previous issues here).
Connected, but only coincidently, with the SIG is that, together with Joachim Baumeister, I organise the annual workshop „Knowledge and Experience Management„, an FGWM event. Its goals is to enable and further the exchange of innovative ideas and practical applications in the field of knowledge and experience management.
And I was busy publishing. Well, I was lucky having such dedicated co-authors. Here are the two submitted and accepted papers for the 18th International Conference on Case-Based Reasoning (ICCBR 2010), Alessandria, Italy:
a.SCatch: Semantic Structure for Architectural Floor Plan Retrieval by Markus Weber, Christoph Langenhan, Thomas Roth-Berghofer, Marcus Liwicki, Andreas Dengel, and Frank Petzold
Abstract. An architect’s daily routine involves working with drawings. They use either a pen or a computer to sketch out their ideas or to do a drawing to scale. We therefore propose the use of a sketch-based approach when using the floor plan repository for queries. This enables the user of the system to sketch a schematic abstraction of a floor plan and search for floor plans that are structurally similar. We also propose the use of a visual query language, and a semantic structure as put forward by Langenhan. An algorithm extracts the semantic structure sketched by the architect on DFKI’s Touch&Write table and compares the structure of the sketch with that of those from the floor plan repository. The a.SCatch system enables the user to access knowledge from past projects easily. Based on CBR strategies and shape detection technologies, a sketch-based retrieval gives access to a semantic floor plan repository. Furthermore, details of a prototypical application which allows semantic structure to be extracted from image data and put into the repository semi-automatically are provided.
Case Acquisition from Text: Ontology-based Information Extraction with SCOOBIE for myCBR by Thomas Roth-Berghofer, Benjamin Adrian, and Andreas Dengel
Abstract. myCBR is a freely available tool for rapid prototyping of similarity-based retrieval applications such as case-based product recommender systems. It provides easy-to-use model generation, data import, similarity modelling, explanation, and testing functionality together with comfortable graphical user interfaces. SCOOBIE is an ontology-based information extraction system, which uses symbolic background knowledge for extracting information from text. Extraction results depend on existing knowledge fragments. In this paper we show how to use SCOOBIE for generating cases from texts. More concrete we use ontologies of the Web of Data, published as so called Linked Data interlinked with myCBR’s case model. We present a way of formalising a case model as Linked Data ready ontology and connect it with other ontologies of the Web of Data in order to get richer cases.
And there is a journal paper forthcoming. It has been accepted for publication in the International Journal on Knowledge Engineering and Datamining.
Improving Understandability of Semantic Search Explanations by Thomas Roth-Berghofer and Björn Forcher
Abstract. Explanation-aware Software Design aims at making software systems smarter in interactions with their users. The long-term goal is to provide methods and tools for systematically engineering understandability into the respective (knowledge-based) software system. In this paper we describe how we improved a semantic search engine, i.e., RadSem, regarding understandability.
The research project MEDICO aims at developing an intelligent, robust and scalable semantic search engine for medical documents. RadSem is based on formal ontologies and designated for different kinds of users. Since semantic search results are often hard to understand an explanation facility for justifying and exploring search results was integrated into RadSem employing the same ontologies used for searching also for explanation generation.
We evaluated the understandability of selected concept labels in an experiment with different user groups using semantic networks as form of depicting explanations and using a class frequency approach for selecting appropriate labels.
Well, so much for now 😉