Number of co-authors:15
Number of publications with 3 favourite co-authors:Lawrence Bergman:5Daniel Oblinger:3Tessa Lau:2
Vittorio Castelli's 3 most productive colleagues in number of publications:Philip S. Yu:39Tessa Lau:21Rachel K. E. Bella..:17
The theory gives the answers, not the theorist.
-- Allen Newell
Read the fascinating history of Wearable Computing, told by its father, Steve Mann
Read Steve's chapter !
Publications by Vittorio Castelli (bibliography)
Castelli, Vittorio, Raghavan, Hema, Florian, Radu, Han, Ding-Jung, Luo, Xiaoqiang and Roukos, Salim (2012): Distilling and exploring nuggets from a corpus. In: Proceedings of the 35th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval 2012. p. 1006.
This paper describes a live and scalable system that automatically extracts information nuggets for entities/topics from a continuously updated corpus for effective exploration and analysis. A nugget is a piece of semantic information that (1) must be mapped semantically to the transitive closure of a pre-defined ontology, (2) is explicitly supported by text, and (3) has a natural language description that completely conveys its semantic to a user. Fig. 1 shows a type of nugget "involvement in events" for a person entity (Leon Panetta): each nugget has a short description ("meeting", "news conference") with a list of supporting passages. Our key contributions are (1) We extract nuggets and remove redundancy to produce a summary of salient information with supporting clusters of passages. (2) We present an entity/topic centric exploration interface that also allows users to navigate to other entities involved in a nugget. (3) We use the statistical NLP technologies developed over the years in the ACE, GALE and TAC-KBP programs, including parsing, mention detection, within and cross document coreference resolution, relation detection and slot filler extraction. (4) Our system is flexible and easily adaptable across domains as demonstrated on two corpora: generic news and scientific papers. Search engines such as Google News and Scholar do not retrieve nuggets, and only remove redundancy at document level. News aggregation applications such as Evri categorize news articles based on the entities of topics but do not extract nuggets. Other systems extract richer information, but not all of it has clear semantics; e.g., Silobreaker presents results as "the relationship between X and Y in the context of [keyphrase]", leaving users with the task of interpreting the semantics as it is not tied to a clear ontology. In contrast we remove redundancy, summarize results and present nuggets that have clear semantics.
© All rights reserved Castelli et al. and/or ACM Press
Castelli, Vittorio and Bergman, Lawrence (2007): Distributed augmentation-based learning: a learning algorithm for distributed collaborative programming-by-demonstration. In: Proceedings of the 2007 International Conference on Intelligent User Interfaces 2007. pp. 160-169.
The learning algorithms used in Programming-by-Demonstration (PBD) are either on-line and incremental or off-line and batch. Neither category is entirely suitable for capturing know-how from demonstrations in a distributed, collaborative environment, where multiple experts can independently provide examples to improve the model. In this paper we describe Distributed Augmentation-Based Learning (DABL), the first real-time PBD learning algorithm suited for distributed know-how acquisition. DABL is an incremental learning algorithm that uses a version-control-like paradigm to combine independently constructed procedure models. An expert can check out a procedure model from a repository and modify it by means of new demonstrations or by manually editing it. The expert then reconciles the changes with those concurrently made by other experts and checked into the repository. DABL automatically merges the two procedures, learns new decision points based on reconcilable differences, and identifies conflicts where there are multiple valid ways of combining the changes or where the combination produces an invalid model, that is, one that does not lie in the search space of the learning algorithm.
© All rights reserved Castelli and Bergman and/or ACM Press
Gweon, Gahgene, Bergman, Lawrence D., Castelli, Vittorio and Bellamy, Rachel K. E. (2007): Evaluating an Automated Tool to Assist Evolutionary Document Generation. In: VL-HCC 2007 - IEEE Symposium on Visual Languages and Human-Centric Computing 23-27 September, 2007, Coeur dAlene, Idaho, USA. pp. 243-248.
Prabaker, Madhu, Bergman, Lawrence and Castelli, Vittorio (2006): An evaluation of using programming by demonstration and guided walkthrough techniques for authoring and utilizing documentation. In: Proceedings of ACM CHI 2006 Conference on Human Factors in Computing Systems 2006. pp. 241-250.
Much existing documentation is informal and serves to communicate "how-to" knowledge among restricted working groups. Using current practices, such documentation is both difficult to maintain and difficult to use properly. In this paper, we propose a documentation system, called DocWizards, that uses programming by demonstration to support low-cost authoring and guided walkthrough techniques to improve document usability. We report a comparative study between the use of DocWizards and traditional techniques for authoring and following documentation. The study participants showed significant gains in efficiency and reduction in error rates when using DocWizards. In addition, they expressed a clear preference for using the DocWizards tool, both for authoring and for following documentation.
© All rights reserved Prabaker et al. and/or ACM Press
Oblinger, Daniel, Castelli, Vittorio and Bergman, Lawrence (2006): Augmentation-based learning: combining observations and user edits for programming-by-demonstration. In: Proceedings of the 2006 International Conference on Intelligent User Interfaces 2006. pp. 202-209.
In this paper we introduce a new approach to Programming-by-Demonstration in which the user is allowed to explicitly edit the procedure model produced by the learning algorithm while demonstrating the task. We describe a new algorithm, Augmentation-Based Learning, that supports this approach by considering both demonstrations and edits as constraints on the hypothesis space, and resolving conflicts in favor of edits.
© All rights reserved Oblinger et al. and/or ACM Press
Bergman, Lawrence, Castelli, Vittorio, Lau, Tessa and Oblinger, Daniel (2005): DocWizards: a system for authoring follow-me documentation wizards. In: Proceedings of the 2005 ACM Symposium on User Interface Software and Technology 2005. pp. 191-200.
Traditional documentation for computer-based procedures is difficult to use: readers have trouble navigating long complex instructions, have trouble mapping from the text to display widgets, and waste time performing repetitive procedures. We propose a new class of improved documentation that we call follow-me documentation wizards. Follow-me documentation wizards step a user through a script representation of a procedure by highlighting portions of the text, as well application UI elements. This paper presents algorithms for automatically capturing follow-me documentation wizards by demonstration, through observing experts performing the procedure. We also present our DocWizards implementation on the Eclipse platform. We evaluate our system with an initial user study that showing that most users have a marked preference for this form of guidance over traditional documentation.
© All rights reserved Bergman et al. and/or ACM Press
Lau, Tessa, Bergman, Lawrence, Castelli, Vittorio and Oblinger, Daniel (2004): Sheepdog: learning procedures for technical support. In: Nunes, Nuno Jardim and Rich, Charles (eds.) International Conference on Intelligent User Interfaces 2004 January 13-16, 2004, Funchal, Madeira, Portugal. pp. 109-116.
Technical support procedures are typically very complex. Users often have trouble following printed instructions describing how to perform these procedures, and these instructions are difficult for support personnel to author clearly. Our goal is to learn these procedures by demonstration, watching multiple experts performing the same procedure across different operating conditions, and produce an executable procedure that runs interactively on the user's desktop. Most previous programming by demonstration systems have focused on simple programs with regular structure, such as loops with fixed-length bodies. In contrast, our system induces complex procedure structure by aligning multiple execution traces covering different paths through the procedure. This paper presents a solution to this alignment problem using Input/Output Hidden Markov Models. We describe the results of a user study that examines how users follow printed directions. We present Sheepdog, an implemented system for capturing, learning, and playing back technical support procedures on the Windows desktop. Finally, we empirically evalute our system using traces gathered from the user study and show that we are able to achieve 73% accuracy on a network configuration task using a procedure trained by non-experts.
© All rights reserved Lau et al. and/or ACM Press
Li, Chung-Sheng, Yu, Philip S. and Castelli, Vittorio (1998): MALM: A Framework for Mining Sequence Database at Multiple Abstraction Levels. In: Gardarin, Georges, French, James C. and Pissinou, Niki (eds.) Proceedings of the 1998 ACM CIKM International Conference on Information and Knowledge Management November 3-7, 1998, Bethesda, Maryland, USA. pp. 267-272.
Thomasian, Alexander, Castelli, Vittorio and Li, Chung-Sheng (1998): Clustering and Singular Value Decomposition for Approximate Indexing in High Dimensional Spaces. In: Gardarin, Georges, French, James C. and Pissinou, Niki (eds.) Proceedings of the 1998 ACM CIKM International Conference on Information and Knowledge Management November 3-7, 1998, Bethesda, Maryland, USA. pp. 201-207.
Show this list on your homepage
Join the technology elite and advance:
Changes to this page (author)23 Nov 2012: Added24 Feb 2010: Modified
16 Jun 2009: Added
29 May 2009: Added
29 May 2009: Added
29 May 2009: Added
24 Jul 2007: Added
24 Jul 2007: Added
19 Jun 2007: Added
11 Jun 2007: Added
28 Apr 2003: Added
Page maintainer: The Editorial Team