Since Artificial Intelligence (AI) software uses techniques like deep lookahead search and stocha... more Since Artificial Intelligence (AI) software uses techniques like deep lookahead search and stochastic optimization of huge neural networks to fit mammoth datasets, it often results in complex behavior that is difficult for people to understand. Yet organizations are deploying AI algorithms in many mission-critical settings. To trust their behavior, we must make AI intelligible, either by using inherently interpretable models or by developing new methods for explaining and controlling otherwise overwhelmingly complex decisions using local approximation, vocabulary alignment, and interactive explanation. This paper argues that intelligibility is essential, surveys recent work on building such systems, and highlights key directions for research.
Proceedings of the 16th international conference on World Wide Web - WWW '07, 2007
The aggregation and comparison of behavioral patterns on the WWW represent a tremendous opportuni... more The aggregation and comparison of behavioral patterns on the WWW represent a tremendous opportunity for understanding past behaviors and predicting future behaviors. In this paper, we take a first step at achieving this goal. We present a large scale study correlating the behaviors of Internet users on multiple systems ranging in size from 27 million queries to 14 million blog posts to 20,000 news articles. We formalize a model for events in these time-varying datasets and study their correlation. We have created an interface for analyzing the datasets, which includes a novel visual artifact, the DTWRadar, for summarizing differences between time series. Using our tool we identify a number of behavioral properties that allow us to understand the predictive power of patterns of use.
Proceedings of the 20th annual ACM symposium on User interface software and technology - UIST '07, 2007
Most of today's GUIs are designed for the typical, able-bodied user; atypical users are, for the ... more Most of today's GUIs are designed for the typical, able-bodied user; atypical users are, for the most part, left to adapt as best they can, perhaps using specialized assistive technologies as an aid. In this paper, we present an alternative approach: SUPPLE++ automatically generates interfaces which are tailored to an individual's motor capabilities and can be easily adjusted to accommodate varying vision capabilities. SUPPLE++ models users' motor capabilities based on a onetime motor performance test and uses this model in an optimization process, generating a personalized interface. A preliminary study indicates that while there is still room for improvement, SUPPLE++ allowed one user to complete tasks that she could not perform using a standard interface, while for the remaining users it resulted in an average time savings of 20%, ranging from an slowdown of 3% to a speedup of 43%.
Proceeding of the twenty-sixth annual CHI conference on Human factors in computing systems - CHI '08, 2008
Page 1. Improving the Performance of Motor-Impaired Users with Automatically-Generated, Ability-B... more Page 1. Improving the Performance of Motor-Impaired Users with Automatically-Generated, Ability-Based Interfaces Krzysztof Z. Gajos Computer Science & Eng. University of Washington Seattle, WA 98195 USA kgajos@cs.washington.edu ...
Proceedings of the 9th international conference on Intelligent user interface - IUI '04, 2004
In order to give people ubiquitous access to software applications, device controllers, and Inter... more In order to give people ubiquitous access to software applications, device controllers, and Internet services, it will be necessary to automatically adapt user interfaces to the computational devices at hand (e.g., cell phones, PDAs, touch panels, etc.). While previous researchers have proposed solutions to this problem, each has limitations. This paper proposes a novel solution based on treating interface adaptation as an optimization problem. When asked to render an interface on a specific device, our Supple system searches for the rendition that meets the device's constraints and minimizes the estimated effort for the user's expected interface actions. We make several contributions: 1) precisely defining the interface rendition problem, 2) demonstrating how user traces can be used to customize interface rendering to particular user's usage pattern, 3) presenting an efficient interface rendering algorithm, 4) performing experiments that demonstrate the utility of our approach.
Proceedings of the 8th international conference on Intelligent user interfaces - IUI '03, 2003
As household appliances grow in complexity and sophistication, they become harder and harder to u... more As household appliances grow in complexity and sophistication, they become harder and harder to use, particularly because of their tiny display screens and limited keyboards. This paper describes a strategy for building natural language interfaces to appliances that circumvents these problems. Our approach leverages decades of research on planning and natural language interfaces to databases by reducing the appliance problem to the database problem; the reduction provably maintains desirable properties of the database interface. The paper goes on to describe the implementation and evaluation of the EXACT interface to appliances, which is based on this reduction. EXACT maps each English user request to an SQL query, which is transformed to create a PDDL goal, and uses the Blackbox planner [13] to map the planning problem to a sequence of appliance commands that satisfy the original request. Both theoretical arguments and experimental evaluation show that EXACT is highly reliable.
Proceedings 17th International Conference on Data Engineering, 2001
For better or for worse, XML has emerged as a de facto standard for data interchange. This consen... more For better or for worse, XML has emerged as a de facto standard for data interchange. This consensus is likely to lead to increased demand for technology that allows users to integrate data from a variety of applications, repositories, and partners which are located across the corporate intranet or on the Internet. Nimble Technology has spent two years developing a product to service this market. Originally conceived after decades of person-years of research on data integration, the product is now being deployed at several Fortune-500 beta-customer sites. This abstract reports on the key challenges we faced in the design of our product and highlights some issues we think require more attention from the research community. In particular, we address architectural issues arising from designing a product to support XML as its core representation, choices in the design of the underlying algebra, on-the-fly data cleaning and caching and materialization policies.
Proceedings of the 4th international conference on Intelligent user interfaces - IUI '99, 1999
Although Programming by Demonstration (PBD) hasthe potential to improve the productivity of unsop... more Although Programming by Demonstration (PBD) hasthe potential to improve the productivity of unsophisticatedusers, previous PBD systems have used brittle,heuristic, domain-specific approaches to execution-tracegeneralization. In this paper we define two applicationindependentmethods for performing generalization thatare based on well-understood machine learning technology. TGen vs uses version-space generalization, andTGen foil is based on the FOIL inductive logic programming algorithm. ...
International Joint Conference on Artificial Intelligence, 2001
Visitors who browse the web from wireless PDAs, cell phones, and pagers are frequently stymied by... more Visitors who browse the web from wireless PDAs, cell phones, and pagers are frequently stymied by web interfaces optimized for desktop PCs. Simply replacing graphics with text and reformatting ta- bles does not solve the problem, because deep link structures can still require minutes to traverse. In this paper we develop an algorithm, MINPATH, that automatically improves wireless web naviga-
International Joint Conference on Artificial Intelligence, 2003
Intelligent agents must function in an uncertain world, containing multiple objects and relations... more Intelligent agents must function in an uncertain world, containing multiple objects and relations that change over time. Unfortunately, no representation is currently available that can handle all these issues, while allowing for principled and efficient inference. This paper ad- dresses this need by introducing dynamic probabilistic relational models (DPRMs). DPRMs are an extension of dynamic Bayesian networks (DBNs) where each
International Joint Conference on Artificial Intelligence, 2001
The fastest growing community of web users is that of mobile visitors who browse with wireless PD... more The fastest growing community of web users is that of mobile visitors who browse with wireless PDAs, cell phones, and pagers. Unfortunately, most web sites today are optimized exclusively for desktop, broadband clients, and deliver content poorly suited for mobile devices — devices that can display only a few lines of text using slow wireless networks. To best serve the
International Conference on Machine Learning, 2000
Machine learning research has been very successful at producing powerful, broadly- applicable cla... more Machine learning research has been very successful at producing powerful, broadly- applicable classification learners. However, many practical learning problems do not fit the classification framework well, and as a re- sult the initial phase of suitably formulating the problem and incorporating the relevant domain knowledge can be very difficult and time-consuming. Here we propose a frame- work to systematize and
International Joint Conference on Artificial Intelligence, 1997
Page 1. Wrapper Induction for Information Extraction by Nicholas Kushmerick A dissertation submit... more Page 1. Wrapper Induction for Information Extraction by Nicholas Kushmerick A dissertation submitted in partial ful llment ... Abstract Wrapper Induction for Information Extraction by Nicholas Kushmerick Chairperson of Supervisory Committee: Professor Daniel S. Weld ...
Principles of Knowledge Representation and Reasoning, 1994
Closed world reasoning is the process of inferring thata logical sentence is false based on its a... more Closed world reasoning is the process of inferring thata logical sentence is false based on its absence froma knowledge base, or the inability to derive it. Previouswork on circumscription, autoepistemic logic,and database theory has explored logical axiomatizationsof closed world reasoning, and investigatedcomputational tractability for propositional theories.Work in planning has traditionally made the closedworld assumption but has avoided closed world reasoning.We
Proceedings of the 18th annual ACM symposium on User interface software and technology - UIST '05, 2005
Decision-theoretic optimization is becoming a popular tool in the user interface community, but c... more Decision-theoretic optimization is becoming a popular tool in the user interface community, but creating accurate cost (or utility) functions has become a bottleneck-in most cases the numerous parameters of these functions are chosen manually, which is a tedious and error-prone process. This paper describes ARNAULD, a general interactive tool for eliciting user preferences concerning concrete outcomes and using this feedback to automatically learn a factored cost function. We empirically evaluate our machine learning algorithm and two automatic query generation approaches and report on an informal user study.
Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '02, 2002
Relational Markov models (RMMs) are a generalization of Markov models where states can be of diff... more Relational Markov models (RMMs) are a generalization of Markov models where states can be of different types, with each type described by a different set of variables. The domain of each variable can be hierarchically structured, and shrinkage is carried out over the cross product of these hierarchies. RMMs make effective learning possible in domains with very large and heterogeneous state spaces, given only sparse data. We apply them to modeling the behavior of web site users, improving prediction in our PROTEUS architecture for personalizing web sites. We present experiments on an e-commerce and an academic web site showing that RMMs are substantially more accurate than alternative methods, and make good predictions even when applied to previously-unvisited parts of the site.
Proceedings of the tenth international conference on World Wide Web - WWW '01, 2001
Page 1. Personalizing Web Sites for Mobile Users Corin R. Anderson University of Washington Seatt... more Page 1. Personalizing Web Sites for Mobile Users Corin R. Anderson University of Washington Seattle, WA, USA corin@cs. washington.edu Pedro Domingos University of Washington Seattle, WA, USA pedrod@cs. washington.edu ...
Since Artificial Intelligence (AI) software uses techniques like deep lookahead search and stocha... more Since Artificial Intelligence (AI) software uses techniques like deep lookahead search and stochastic optimization of huge neural networks to fit mammoth datasets, it often results in complex behavior that is difficult for people to understand. Yet organizations are deploying AI algorithms in many mission-critical settings. To trust their behavior, we must make AI intelligible, either by using inherently interpretable models or by developing new methods for explaining and controlling otherwise overwhelmingly complex decisions using local approximation, vocabulary alignment, and interactive explanation. This paper argues that intelligibility is essential, surveys recent work on building such systems, and highlights key directions for research.
Proceedings of the 16th international conference on World Wide Web - WWW '07, 2007
The aggregation and comparison of behavioral patterns on the WWW represent a tremendous opportuni... more The aggregation and comparison of behavioral patterns on the WWW represent a tremendous opportunity for understanding past behaviors and predicting future behaviors. In this paper, we take a first step at achieving this goal. We present a large scale study correlating the behaviors of Internet users on multiple systems ranging in size from 27 million queries to 14 million blog posts to 20,000 news articles. We formalize a model for events in these time-varying datasets and study their correlation. We have created an interface for analyzing the datasets, which includes a novel visual artifact, the DTWRadar, for summarizing differences between time series. Using our tool we identify a number of behavioral properties that allow us to understand the predictive power of patterns of use.
Proceedings of the 20th annual ACM symposium on User interface software and technology - UIST '07, 2007
Most of today's GUIs are designed for the typical, able-bodied user; atypical users are, for the ... more Most of today's GUIs are designed for the typical, able-bodied user; atypical users are, for the most part, left to adapt as best they can, perhaps using specialized assistive technologies as an aid. In this paper, we present an alternative approach: SUPPLE++ automatically generates interfaces which are tailored to an individual's motor capabilities and can be easily adjusted to accommodate varying vision capabilities. SUPPLE++ models users' motor capabilities based on a onetime motor performance test and uses this model in an optimization process, generating a personalized interface. A preliminary study indicates that while there is still room for improvement, SUPPLE++ allowed one user to complete tasks that she could not perform using a standard interface, while for the remaining users it resulted in an average time savings of 20%, ranging from an slowdown of 3% to a speedup of 43%.
Proceeding of the twenty-sixth annual CHI conference on Human factors in computing systems - CHI '08, 2008
Page 1. Improving the Performance of Motor-Impaired Users with Automatically-Generated, Ability-B... more Page 1. Improving the Performance of Motor-Impaired Users with Automatically-Generated, Ability-Based Interfaces Krzysztof Z. Gajos Computer Science & Eng. University of Washington Seattle, WA 98195 USA kgajos@cs.washington.edu ...
Proceedings of the 9th international conference on Intelligent user interface - IUI '04, 2004
In order to give people ubiquitous access to software applications, device controllers, and Inter... more In order to give people ubiquitous access to software applications, device controllers, and Internet services, it will be necessary to automatically adapt user interfaces to the computational devices at hand (e.g., cell phones, PDAs, touch panels, etc.). While previous researchers have proposed solutions to this problem, each has limitations. This paper proposes a novel solution based on treating interface adaptation as an optimization problem. When asked to render an interface on a specific device, our Supple system searches for the rendition that meets the device's constraints and minimizes the estimated effort for the user's expected interface actions. We make several contributions: 1) precisely defining the interface rendition problem, 2) demonstrating how user traces can be used to customize interface rendering to particular user's usage pattern, 3) presenting an efficient interface rendering algorithm, 4) performing experiments that demonstrate the utility of our approach.
Proceedings of the 8th international conference on Intelligent user interfaces - IUI '03, 2003
As household appliances grow in complexity and sophistication, they become harder and harder to u... more As household appliances grow in complexity and sophistication, they become harder and harder to use, particularly because of their tiny display screens and limited keyboards. This paper describes a strategy for building natural language interfaces to appliances that circumvents these problems. Our approach leverages decades of research on planning and natural language interfaces to databases by reducing the appliance problem to the database problem; the reduction provably maintains desirable properties of the database interface. The paper goes on to describe the implementation and evaluation of the EXACT interface to appliances, which is based on this reduction. EXACT maps each English user request to an SQL query, which is transformed to create a PDDL goal, and uses the Blackbox planner [13] to map the planning problem to a sequence of appliance commands that satisfy the original request. Both theoretical arguments and experimental evaluation show that EXACT is highly reliable.
Proceedings 17th International Conference on Data Engineering, 2001
For better or for worse, XML has emerged as a de facto standard for data interchange. This consen... more For better or for worse, XML has emerged as a de facto standard for data interchange. This consensus is likely to lead to increased demand for technology that allows users to integrate data from a variety of applications, repositories, and partners which are located across the corporate intranet or on the Internet. Nimble Technology has spent two years developing a product to service this market. Originally conceived after decades of person-years of research on data integration, the product is now being deployed at several Fortune-500 beta-customer sites. This abstract reports on the key challenges we faced in the design of our product and highlights some issues we think require more attention from the research community. In particular, we address architectural issues arising from designing a product to support XML as its core representation, choices in the design of the underlying algebra, on-the-fly data cleaning and caching and materialization policies.
Proceedings of the 4th international conference on Intelligent user interfaces - IUI '99, 1999
Although Programming by Demonstration (PBD) hasthe potential to improve the productivity of unsop... more Although Programming by Demonstration (PBD) hasthe potential to improve the productivity of unsophisticatedusers, previous PBD systems have used brittle,heuristic, domain-specific approaches to execution-tracegeneralization. In this paper we define two applicationindependentmethods for performing generalization thatare based on well-understood machine learning technology. TGen vs uses version-space generalization, andTGen foil is based on the FOIL inductive logic programming algorithm. ...
International Joint Conference on Artificial Intelligence, 2001
Visitors who browse the web from wireless PDAs, cell phones, and pagers are frequently stymied by... more Visitors who browse the web from wireless PDAs, cell phones, and pagers are frequently stymied by web interfaces optimized for desktop PCs. Simply replacing graphics with text and reformatting ta- bles does not solve the problem, because deep link structures can still require minutes to traverse. In this paper we develop an algorithm, MINPATH, that automatically improves wireless web naviga-
International Joint Conference on Artificial Intelligence, 2003
Intelligent agents must function in an uncertain world, containing multiple objects and relations... more Intelligent agents must function in an uncertain world, containing multiple objects and relations that change over time. Unfortunately, no representation is currently available that can handle all these issues, while allowing for principled and efficient inference. This paper ad- dresses this need by introducing dynamic probabilistic relational models (DPRMs). DPRMs are an extension of dynamic Bayesian networks (DBNs) where each
International Joint Conference on Artificial Intelligence, 2001
The fastest growing community of web users is that of mobile visitors who browse with wireless PD... more The fastest growing community of web users is that of mobile visitors who browse with wireless PDAs, cell phones, and pagers. Unfortunately, most web sites today are optimized exclusively for desktop, broadband clients, and deliver content poorly suited for mobile devices — devices that can display only a few lines of text using slow wireless networks. To best serve the
International Conference on Machine Learning, 2000
Machine learning research has been very successful at producing powerful, broadly- applicable cla... more Machine learning research has been very successful at producing powerful, broadly- applicable classification learners. However, many practical learning problems do not fit the classification framework well, and as a re- sult the initial phase of suitably formulating the problem and incorporating the relevant domain knowledge can be very difficult and time-consuming. Here we propose a frame- work to systematize and
International Joint Conference on Artificial Intelligence, 1997
Page 1. Wrapper Induction for Information Extraction by Nicholas Kushmerick A dissertation submit... more Page 1. Wrapper Induction for Information Extraction by Nicholas Kushmerick A dissertation submitted in partial ful llment ... Abstract Wrapper Induction for Information Extraction by Nicholas Kushmerick Chairperson of Supervisory Committee: Professor Daniel S. Weld ...
Principles of Knowledge Representation and Reasoning, 1994
Closed world reasoning is the process of inferring thata logical sentence is false based on its a... more Closed world reasoning is the process of inferring thata logical sentence is false based on its absence froma knowledge base, or the inability to derive it. Previouswork on circumscription, autoepistemic logic,and database theory has explored logical axiomatizationsof closed world reasoning, and investigatedcomputational tractability for propositional theories.Work in planning has traditionally made the closedworld assumption but has avoided closed world reasoning.We
Proceedings of the 18th annual ACM symposium on User interface software and technology - UIST '05, 2005
Decision-theoretic optimization is becoming a popular tool in the user interface community, but c... more Decision-theoretic optimization is becoming a popular tool in the user interface community, but creating accurate cost (or utility) functions has become a bottleneck-in most cases the numerous parameters of these functions are chosen manually, which is a tedious and error-prone process. This paper describes ARNAULD, a general interactive tool for eliciting user preferences concerning concrete outcomes and using this feedback to automatically learn a factored cost function. We empirically evaluate our machine learning algorithm and two automatic query generation approaches and report on an informal user study.
Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '02, 2002
Relational Markov models (RMMs) are a generalization of Markov models where states can be of diff... more Relational Markov models (RMMs) are a generalization of Markov models where states can be of different types, with each type described by a different set of variables. The domain of each variable can be hierarchically structured, and shrinkage is carried out over the cross product of these hierarchies. RMMs make effective learning possible in domains with very large and heterogeneous state spaces, given only sparse data. We apply them to modeling the behavior of web site users, improving prediction in our PROTEUS architecture for personalizing web sites. We present experiments on an e-commerce and an academic web site showing that RMMs are substantially more accurate than alternative methods, and make good predictions even when applied to previously-unvisited parts of the site.
Proceedings of the tenth international conference on World Wide Web - WWW '01, 2001
Page 1. Personalizing Web Sites for Mobile Users Corin R. Anderson University of Washington Seatt... more Page 1. Personalizing Web Sites for Mobile Users Corin R. Anderson University of Washington Seattle, WA, USA corin@cs. washington.edu Pedro Domingos University of Washington Seattle, WA, USA pedrod@cs. washington.edu ...
Uploads
Papers by Daniel Weld