Publication: “Evaluating the Intelligibility of Medical Ontological Terms”

Understandability is a key challenge in explanation provision and estimating well what users may already know can help offering better explanations.

Abstract. The research project MEDICO aims at developing an intelligent, robust and scalable semantic search engine for medical documents. The search engine of the MEDICO demonstrator RadSem is based on formal ontologies and is designated for different kinds of users, such as medical doctors, medical IT professionals, patients, and policy makers. Since semantic search results are not always self-explanatory, explanations are necessary to support requirements of different user groups. For this reason, an explanation facility is integrated into RadSem employing the same ontologies for explanation generation. In this work, we present a user experiment that evaluates the intelligibility of labels provided by the used ontologies with respect to different user groups. We discuss the results for refining our current approach for explanation generation in order to provide understandable justifications of semantic search results. Here, we focus on medical experts and laymen, respectively, using semantic networks as form of depiction.
[Björn Forcher, Kinga Schumacher, Michael Sintek, and Thomas Roth-Berghofer. Evaluating the intelligibility of medical ontological terms. In Joachim Baumeister and Grzegorz J. Nalepa, editors, Proceedings of the 5th Workshop on Knowledge Engineering and Software Engineering (KESE-2009), http://CEUR-WS.org/Vol-486/.]

Touch & Write Table: Collaborative Knowledge Tool

Social knowledge management, in general, and collaborative knowledge representation, in particular, need the right tools for assisting in these tasks. The touch and write table, developed at the knowledge management research department provides just that. Just watch the short video on YouTube.

Yes, you can think like a designer!

In my research on explanation-awareness I am looking very often into what designers do or don’t do (see elsewhere on my blog). If one already has a complex software tool that one wants to enhance with explanation capabilities it surely does not help to overwhelm the user with additional explanatory information, one needs to carefully design the explanation capabilities and the explanations. Garr Reynolds compiled a nice list of tips that I’d like to promote here:

Most people do not really think about design and designers, let alone think of themselves as designers. But what, if anything, can regular people — teachers, students, business people of all types — learn from designers and from thinking like a designer? And what of more specialized professions? Can medical doctors, scientists, researchers, and engineers, and other specialists in technical fields benefit in anyway by learning how a graphic designer or interaction designer thinks? Is there something designers, either through their training or experience, know that we don’t? I believe there is.

[From Presentation Zen: 10 Tips on how to think like a designer]

[composed and posted with ecto]

Pushing explanations back into the spotlight

Participants of ExaCt 2009 on day #1

The ability to explain reasoning processes and results can substantially affect the usability and acceptance of a software system. There is no doubt about it. Unfortunately, the topic of explanation has not received proper attention since the demise of expert systems research during the “AI winter”. Only recently explanation is seen as a research topic in its own right again. At my last workshop on Explanation-aware computing ExaCt 2009, organised and held together with Nava Tintarev and David B. Leake at IJCAI-09 in Pasadena, CA, several more renowned researchers joined my effort of pushing and promoting the topic of explanation; among them Deborah McGuinness (RPI, USA), Anind Dey (CMU, USA), Ashok Goel (Georgia Tech, USA), Doug Walton (U. of Windsor, CA), and Miltos Petridis (U. of Greenwich, UK). (More researchers can be found on my dedicated website on-explanation.net.)

So, what do I want to achieve?

First, I want to make software designers and developers aware of explanations. In the long run, I also want software systems to become explanation-aware. I want to promote the notion of explanation as a research topic in its own right in order to develop respective engineering methods.

How to get there

A lot of inspiration came from Edward Tufte’s book Visual Explanations, which I stumbled upon by accident on the desk of a former colleague, years before I took an active interest in explanation. Edward Tufte invites the reader to

enter the cognitive paradise of explanation, a sparkling and exuberant world, intensely relevant to the design of information.

As Artificial Intelligence is about simulating human intelligence, we AI researchers should take Tufte’s words to heart. In AI, we strive—not only but also—for the goal that AI systems become able to discover explanations themselves and that they represent them appropriately in order to communicate with their users. Until that goal is reached, we should at least provide such systems with pre-formulated explanations and representation templates to support human users in their interaction with the system.

Within the field of knowledge-based systems, explanations are considered as an important link between humans and machines. Their main purpose is to increase the confidence of the user in the system’s result (persuasion) or the system as a whole (satisfaction), by providing evidence of how the solution was derived (transparency). Explanations are part of human understanding processes and part of most dialogues, and, therefore, need to be incorporated into system interactions. But looking at all the efforts already invested in explanation research, I think, we have just rattled at the gates of the above mentioned cognitive paradise.

A helpful tool for designing and developing software systems from an explanation-aware viewpoint is the general explanation scenario depicted here with three participants: user, originator, and explainer. The user communicates by way of a user interface (UI) with the whole software system and is the recipient of explanations. The originator is the tool the user works with to perform tasks and solve problems. The explainer can be seen as another tool that helps understanding how the originator works and what knowledge the originator uses. Please note that this scenario is simplifying in so far as it does not consider the case where the software system asks the user for explanations or justifications.

Explainer and originator need to have knowledge about each other. The originator needs to provide knowledge about its reasoning process as well as intermediate results and decisions in order to allow the explainer to generate good explanations. The relationship between explainer and originator is somewhat asymmetrical regarding the used knowledge. Whereas the explainer needs to have access to the originator’s knowledge-base (in addition to its explanation supporting knowledge-base) this does not hold for the originator. For its problem-solving task the originator does not need to have access to the explainer’s knowledge-base, but the originator needs to be aware of it in order to fill it appropriately.

Community building

Making people—researchers, software designers and developers, and, not to forget, funding organisations—aware of explanation-awareness (pun intended) is not a one-man show but a community effort. At last year’s ExaCt 2008 the idea of a manifesto came up as a way of expressing goals of the developing explanation community. A first version is available here.

If you would like to participate in further discussions or just like to receive further information on this topic and about future workshops you might consider joining the Yahoo!-group explanation-research. You think you or someone else belongs on the list of explanation researchers? Drop me a line and a URL to their  homepage and indicate relevant research.

Short attention spans? I don’t think so … anymore

I admit I believed very much in that youths today have a much shorter attention span than us “older people”, i.e., people over thirty, and that they needed to be entertained more and more. Media repeat this over and over, and I spotted this lack of attention in all of my classes. But, the last two weeks showed to me that this might be also some kind of self-fulfilling prophecy: If one expects some behaviour, one will get it.

DFKI’s knowledge management department keeps good relations to several secondary schools, one of it Hugo-Ball-Gymnasium (HBG) in Pirmasens. A few years ago I was involved in re-establishing the contact with HBG. We did a small project there on eLearning. Since then DFKI researchers regularly give talks on Artificial Intelligence and related topics.

Like last year, Benjamin Adrian organised a two weeks internship with the computer science and math teachers of HBG. Five 11th grade students participated in the programme, which consisted of a presentation each day accompanied by exercises. Two DFKI management interns joined the talks. The presentations ranged from such topics as “Semantic Desktop”, “Web 2.0 and the ALOE platform”, “Intelligent Text Processing” to “Computer-generated explanations”. I contributed an introductory talk on AI and second talk “Case-Based Reasoning and Explanations”.

During my first talk I already noticed the rapt attention of the students. I have to admit that I felt a bit uncomfortable at first as I was not used to that level of attention. These young people did not only listen closely to what I had to say, they participated and answered questions that typically became rhetorical questions in university lectures. They even asked questions on their own.

I was asked to limit my talks to about an hour, but I enjoyed the presentations so much that I extended the first a bit. When it came to the second talk I extended it to nearly two hours. I hurled a lot of stuff at them, but they seemed eager to learn and understand. I am sure a lot went right over their heads, but they did not seem to tire (unlike me).

Of course, one could say the students chose this internship and, thus, were very much interested in what we presented. On the other hand, they could have chosen to lounge about during the two weeks. But no, each of them stayed tuned until the very end of my presentations (I heard the same from my colleagues, mind you). I do not think of myself as being a very good or pedagogically gifted teacher who could motivate even the dead. So it must be their fault. They have just a normal attention span, if they are interested in a topic. Just like us “older people”.

I try to be a little bit less prejudiced in this regard when the next lecture at university starts. Instead of looking out for signs of lacking attention I will look out more for signs of attention and interest.

Hunch – Hilfe in allen Lebenslagen? – heute.de Nachrichten

Letzten Freitag erhielt ich einen Anruf von Georg H. Przikling, Online-Redakteur der Sparte Computer der heute.de-Nachrichten. Im Telefonat durfte ich zum brandneuen Portal hunch.com Stellung nehmen. Hier das Ergebnis: Hunch – Hilfe in allen Lebenslagen? – heute.de Nachrichten.

The nature of the Semantic Web

Just a pointer to an interesting summary by one of the pioneers of the Semantic Web, Jim Hendler:

The Semantic Web is based on the relatively straightforward idea that to be able to integrate (link) data on the Web we must have some mechanism for knowing what relationships hold among the data, and how that relates to some “real world” context. Read on here …

[From What is the Semantic Web really all about? - Web Science - the World of the World Wide Web - James Hendler's blog on Nature Network]

Indeed, why dots?

A while ago I blogged about Scott McCloud’s book “Understanding comics – The invisible art” (see understanding ontologies). I just came across a presentation (via Garr Reynolds’ Presentation Zen) that shows the use of abstraction in a very nice way.

Gute Lehre(r) an der TU Kaiserslautern

Schön, wenn man so gute Kollegen wie Achim Ebert am DFKI bzw. am Fachbereich Informatik der TU KL hat:

Am 28. 4. 2009 wird der Fachbereich Informatik zum vierten Mal in Folge auf dem Tag der Lehre ausgezeichnet. Mit J.-Prof. Ebert erhält zum vierten Mal ein Professor des Fachbereichs einen persönlichen Lehrpreis des Landes.

[From FB-Informatik (TU-KL): Newsletter FB Informatik, 1/2009]

Ricoh and Java Developer Challenge

Hungary (Zoltan Szabo & Balazs Lajer from University of Pannonia) won, by a hair ahead of Germany. Congratulations to all the students and professors involved. [From Ricoh and Java Developer Challenge - Octavian Tanase's Weblog]

Congratulations to my students, Markus Weber and Volker Hudlet, who had participated in this year’s Ricoh & Java Developer challenge. After having won the national competition, being awarded second place in the international competition is quite an accomplishment.

Markus and Volker developed a prototypical recommender system based on context-aware service discovery using case-based reasoning methods for a Ricoh multi-functional product (MFP). They successfully combined the open-source tool myCBR and the jColibri framework. They were co-supervised by my colleague Heiko Maus and me.