EXPLANATION-AWARE COMPUTING (ExaCt 2009)

-
Call for papers, for the 4th International and IJCAI-09 Workshop on
EXPLANATION-AWARE COMPUTING (ExaCt 2009)

11-12 July 2009, Pasadena, CA, USA
Paper submission deadline: March 6, 2009**


Both within AI systems and in interactive systems, the ability to explain reasoning processes and results can have substantial impact. Within the field of knowledge-based systems, explanations have been considered as an important link between humans and machines. There, their main purpose has been 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 it was derived (transparency). More recently, in recommender systems good explanations have also been used to help to inspire user trust and loyalty (trust), and make it quicker and easier (efficiency) for users to find what they want (effectiveness). Additional AI research has focused on how computer
systems can themselves use explanations, for example to form new generalizations (learning). Explanations have also been used to increase the external user's understanding of a domain (education).

Current interest in mixed-initiative systems provides a new context in which explanation issues may play a crucial role. When knowledge-based systems are partners in an interactive socio-technical process, with incomplete and changing problem descriptions, communication between human and software systems is a central part. Thus explanations exchanged between human agents and software agents may play an important role in mixed-initiative problem solving.

This workshop series aims to draw on multiple perspectives on explanation, to examine how explanation can be applied to further the development of robust and dependable systems, and increase transparency, user sense of control (scrutability), trust, acceptance and decision support.

If you would like to participate in discussions on this topic or like to receive further information about this workshop you might consider joining the Yahoo!-group.

Information on explanation research is also collected at http://on-explanation.net.

GOALS AND AUDIENCE
We invite original contributions to the research on explanations from a variety of areas and communities such as computer science, cognitive science, linguistics, philosophy of science, psychology, and education. In addition to presentations and discussions of invited contributions and invited talks, this workshop will offer organised and open sessions for targeted discussions and creating an interdisciplinary community. Demonstration sessions will provide the opportunity to showcase explanation-enabled/-aware applications.

TOPICS OF INTEREST
Suggested topics for contributions (not restricted to IT views):
Models and knowledge representations for explanations
Integrating application and explanation knowledge
Explanation-awareness in (designing) applications
Methodologies for developing explanation-aware systems
Explanations and learning
Context-aware explanation vs. explanation-aware context
Confidence and explanations
Privacy, security, trust, and explanation
Empirical studies of explanations
Requirements and needs for explanations to support human understanding
Explanation of complex, autonomous systems
Co-operative explanation
Visualising explanations
Dialogue management and natural language generation

Submissions on additional topics are welcome as well.

SUBMISSIONS AND STYLE
Workshop submissions will be electronic, in pdf format only, using the EasyChair submission system linked from the workshop website.

Papers must be written in English and not exceed 12 pages in the Springer LNCS format. At least one author of each accepted paper must register for the workshop and present the contribution in order to be published in the workshop proceedings. The organising committee is considering editing a special issue of an appropriate international journal (e.g., Kluwer’s Knowledge-based Systems, Elsevier’s Expert Systems with Applications, or Springer’s
Information System Frontiers) depending on the number and quality of the submissions.

Those wishing to participate providing a live system demonstration should submit a proposal (1-2 pages). Those wishing to participate without paper or demo submission should submit a brief synopsis of their relevant work or at least a brief statement of interest.

Non-archival working notes will be produced containing the papers presented at the workshop.

If you have questions please contact the chairs at this email address.

IMPORTANT DATES
Submission deadline: March 6, 2009
Notification of acceptance: April 17, 2009
Camera-ready versions of papers: May 8, 2009
IJCAI-09 Workshop Program: July 11-12, 2009


WORKSHOP SCHEDULE
The schedule will be made available on the workshop website. See the workshop website for an agenda overview und links to past workshops.


INVITED TALKS
Talks by two invited speakers, each representing a different community addressing explanation issues, are planned.


CHAIRS
Thomas R. Roth-Berghofer, German Research Center for Artificial Intelligence DFKI GmbH, Germany
thomas.roth-berghofer at dfki de

Nava Tintarev, Department of Computer Science, University Of Aberdeen, UK
n.tintare at abdn ac uk

David B. Leake
Computer Science Department, Indiana University, USA
leake at cs indiana edu


PROGRAMME COMMITTEE
Agnar Aamodt, Norwegian Uni of Science and Technology (NTNU)
David W. Aha, Navy Center for Applied Research in AI, USA
Patrick Brézillon, LIP6, France
Jörg Cassens, NTNU
Francisco Javier Díez, UNED Madrid, Spain
Babak Esfandiari, Carleton University, Canada
Pierre Grenon, IFOMIS, University of Saarbrücken, Germany
Anders Kofod-Petersen, SINTEF, Norway
Hector Muñoz-Avila, Lehigh University, USA
Paulo Pinheiro da Silva, University of Texas, El Paso, USA
Enric Plaza, IIIA-CSIC, Spain
Michael M. Richter, University of Calgary, Canada
Sven Schwarz, DFKI, Germany
Gheorghe Tecuci, George Mason University, Fairfax, VA, USA
Douglas Walton, University of Winnipeg, Canada

Comments

Post a Comment

Popular posts from this blog

On the importance of being pedantic (series: notes to myself)

-
Image
They say that to call someone pedantic is an insult. I'm not so sure. True, someone pedantic is obsessed with minor details, small errors, or tiny imperfections. And a pedantic is also someone who cares too much about all such things not to let you know about them, advising or correcting, disagreeing or disapproving. And yes, if you are a pedant, you are more than just occasionally pedantic. This can happen to anybody, the excessive emphasis on some narrow or boring detail being a tendency we all share when it comes to matters about which we care very much. But if you are a pedant, being pedantic is your daily stance, your intrinsic nature, your way of living. You are always, consistently, reliably, systematically pedantic, from the moment you wake up, about the exact place where the slippers should be next to your bed, all the way to the moment you go to sleep, and the exact place where the phone should be placed to recharge. If you are a true pedant, no detail is too trivial, no
Read more

Mind the app - considerations on the ethical risks of COVID-19 apps

-
[22 April update: at the Digital Ethics Lab (OII, University of Oxford) we have elaborated a list of 16 questions to check whether an app is ethically justifiable, the full article, open access, is available here ] There is a lot of talk about apps to deal with the pandemic . Some of the best solutions use the Bluetooth connection of mobile phones to determine the contact between people and therefore the probability of contagion. In theory, it may seem simple. In practice, there are several ethical problems, not only legal and  technical ones . To understand them, it is useful to distinguish between the validation and the verification of a system.  The validation of a system answers the question: "are we building the right system?". The answer is no if the app is illegal,  for example, the use of an app in the EU must comply with the GDPR; mind that this is necessary but not sufficient to make the app also ethically acceptable, see below; is unnecessary, f
Read more

On being mansplained (series: notes to myself)

-
I wanted to make a brief point. I thought it was original. But I was too late, it had already been made: mansplaining is gender-neutral . I know because I have had people explaining to me – your average Caucasian, male, middle-aged, European bourgeoisie, in other words, the stereotype of the mansplainer – how to spell my name. But let me hasten to say that, no, my dear, this is not literally, thank you for explaining to me that it cannot be the case. I meant it metaphorically. What puzzles me is how can you be so sure that you are not the one who is not getting it? Please pause for a moment and ask yourself whether "o buraco é mais embaixo", as they say in Brazil, which roughly means that "the hole is further down". And if it looks obvious to you, if you thought about it, why do you assume I did not? In short, next time, if you see me behind you, please do wonder whether I might be almost a whole lap ahead, before explaining to me how to run.
Read more

Call for expressions of interest: research position for a project on Digital Sovereignty and the Governance, Ethical, Legal, and Social Implications (GELSI) of digital innovation.

-
Image
THIS CALL IS NOW CLOSED Call for expressions of interest: research position for a project on Digital Sovereignty and the Governance, Ethical, Legal, and Social Implications (GELSI) of digital innovation. The Centre for Digital Ethics of the University of Bologna https://centri.unibo.it/digital-ethics/en invites expressions of interest (EOI) from early career researchers, with a relevant Master or PhD degree, interested in developing a research project in the field of Digital Sovereignty and the Governance, Ethical, Legal, and Social Implications (GELSI) of digital innovation. The EOI should include three documents (all in English): 1. a letter (ca. 500 words), including relevant details about personal motivation, relevant skills, experience, and a link to a Google Scholar profile; 2. a short CV (max 3 pages), including a list of publications; and 3. a short (ca. 1,000 words) outline of the proposed research project about digital sovereignty and the GELSI of digital innovat
Read more

Il sapore della felicità condivisa

-
Il 19 marzo del 1850, Charlotte Brönte scrive una lettera a William Smith Williams, l’editore presso Smith Elder che per primo aveva riconosciuto in lei una straordinaria scrittrice. Williams le ha inviato alcuni libri da leggere, e lei, nel ringraziarlo, usa una frase divenuta famosa e che oggi troviamo citata ovunque: “la felicità non condivisa può a malapena essere chiamata felicità. Non ha sapore/gusto.” (Happiness quite unshared can scarcely be called happiness—it has no taste). Per le persone misantrope e asociali, o anche semplicemente un po’ solitarie, che ritengono che la solitudine sia l’unica felicità (beata solitudo, sola beatitudo), l’affermazione sembra del tutto errata. Eppure, è difficile non riconoscere che esiste un tipo di felicità che richiede la sua condivisione per essere goduta a pieno e non restare incompleta. Non si tratta della felicità intesa come contentezza. Come si sa, questa fa riferimento allo stare bene con se stessi e con la propria vita, in pace con l
Read more

On the art of biting one's own tongue (series: notes to myself)

-
The art of biting one's own tongue consists in the ability not to engage when someone says something unpleasant, untrue, malicious, or abusive about you. Instead of answering a biased question, arguing against a ludicrous opinion, complaining about an abusive message, correcting a meaningless error, countering a fallacy, explaining a patent mistake, objecting to a groundless criticism, rectifying a willful misrepresentation, rejecting an insinuation, responding to a provocation, retorting to a nasty remark, replying to an offensive allegation, … in short, instead of engaging with your mindless interlocutors you simply ignore them and do absolutely nothing, not even acknowledging that you might have received their communication, not even sharing a “no comment”, just silence. As far as they know, you might have never got the email, read the tweet or the Facebook comment, seen the Instagram picture. If you bite your own tongue appropriately, for them their communication might have nev
Read more

Call for Papers for American Philosophical Quarterly’s special issue on The Ethics of Artificial Intelligence

-
Image
Call for Papers for American Philosophical Quarterly ’s special issue on The Ethics of Artificial Intelligence Editor in chief: Patrick Grim Guest editor: Luciano Floridi Artificial Intelligence (AI), from machine learning to robotics, generates enormous opportunities and significant challenges. In the past few years, many of them have led to a flourishing of international initiatives and growing research concerning the ethics and governance of AI. This special issue solicits the submission of original articles that investigate how AI is transforming classic questions or leading to new ones in moral thinking, and how such questions may be addressed successfully. Topics of special interest include but are not limited to AI and: authenticity, creativity, and intellectual property rights; bias, discrimination and fairness; the digital divide; digital sovereignty; capabilities and empowerment; cyberconflicts and cybersecurity; fake news and deep fakes; ethical frameworks and principles; et
Read more

Gauss Professorship

-
Image
Every year, the Göttingen Academy of Sciences (Akademie der Wissenschaften zu Göttingen) elects a Gauss Professor (Gauß-Professur der Akademie der Wissenschaften zu Göttingen) to honour the memory of the great scientist . Normally, the Professorship is awarded to an "importat scientist in one of Gauss' fields of interest". So, no philosopher has been elected so far. They just made an exception. Next year, I will be their Gauss Professor, in recognition of my work on the philosophy of information. An overwhelming honour, but very exciting. No teaching, complete freedom of research and great support. Shame on me if I do not make the most of such a privilege. I better start revising my German.
Read more

The ethics of WikiLeaks

-
The Wikileaks phenomenon is intricate, but suppose we reduce its ethical evaluation to two questions: is whistleblowing ethical, even when motivated by resentment and the desire to harm its target? And is Wikileaks’ facilitation of whistleblowing ethical, even if it might put at risk innocent people? A deontologist, convinced that telling the truth and never lying is an absolute must, is likely to appreciate whistleblowing as the right thing to do, independently of the reasons behind it. And a consequentialist may support Wikileaks as a means to maximise the welfare of the largest number of people, especially if risks are minimized by censuring sensitive information. So current answers in the mass media seem to converge: Wikileaks is a good thing. I am not entirely convinced. Confidential communication is a three-player game – sender, receiver and referent – in which sender and receiver trust each other. The receiver, not the referent, trusts and holds responsible the sender f
Read more

The Loebner Prize from a judge's perspective

-
Image
This year, for the first time in its history, the Loebner Prize competition was held in England, at the University of Reading to be precise. It was organised by Kevin Warwick and Huma Shah. Independently of whether Turing might have been pleased (he was not well treated in this country, recall?), there was a satisfying sense of “coming home” of the Turing Test (henceforth TT ). Expectations were high, and they very highly advertised too. The meeting was perfectly organised. Having been invited to play the role of a judge, together with several other colleagues, including two members of the IEG , Mariarosaria Taddeo and Matteo Turilli ( here are their pictures and Rosaria's interview ) , I enjoyed the opportunity to see from close-up the machinery and the TT . It was intriguing and great fun. Because there were interviews with the BBC and other things going on, and because we were also supposed to take part in the parallel AISB Symposium on the TT , I had time to test only
Read more