Keywords

Artificial Intelligence, machine learning, computational linguistics, knowledge management, cognitive computing, natural language processing, data & text mining, text analytics, neural networks, unstructured information management

Summary

Artificial Intelligence/machine learning researcher with expertise in automated natural language processing. Extensive experience in designing adaptive, language-using applications and in directing research projects that study how humans and automated systems learn and use language.

Work experience

Senior Research Engineer, Fox Interactive Media, Los Angeles, CA, 2008 - present.

Principal Computer Scientist, MetaLINCS, San Jose, CA, 2007

Senior Scientist/Director of Research, H5 Technologies, San Francisco, CA, 2005 - 2007.

Senior Engineer & Project Lead, Entrieva, Reston, VA, 2003 - 2005.

Principal Scientist, Comprecorp, Nevada City, CA, 2001.

Senior Engineer, Ask Jeeves, Emeryville, CA, 1999 - 2000.

Postdoctoral Research Associate, Carnegie Mellon Univ., 1995 - 1998.

Tutor, Neural Network Training Program, U.C., San Diego, 1991.

Research Assistant, Brown Univ., 1987 - 1989.

Skills and research interests

Platforms: Windows, UNIX, VMS, MacOS.

Languages: Java (8 years), C (10+ years), C++ (9 years), SAS (10+ years)

Experiment-related skills: Extensive experience with all aspects of experimental psychology research, including background literature search, hypothesis development, and design of experiment, experimental control system, experimental protocols and appropriate statistical analyses (including relevant computer applications).

Research interests: Language processing and language acquisition in humans and connectionist networks, large scale cognitive systems, connectionist models of second-language acquisition and lexical acquisition/processing, effects of working memory and other aspects of the general cognitive system on language.

Projects and publications

MetaLINCS. Innovation team. Languages & operating systems: Java, C++, Windows, UNIX. Support innovations and improvements to MetaLINCS flagship e-discovery application. This requires a) a complete understanding of both the current product and its embedded algorithms as well as other algorithms that might be of potential benefit, b) expert skill in Java, and c) expertise in a wide variety of natural language processing algorithms. 2007-present.

H5. Lead research and development. Languages & operating systems: Java, Windows, UNIX. Research and develop improvements to business processes in order to increase accuracy and speed and lower cost. This requires a complete understanding of research and analytical methodologies needed to evaluate the performance of the business processes, especially as they relate to large scale document analysis. 2005-2007.

Build software tools. Using Java and Java Server Faces (JSF), act as part of the H5 Technologies software team to architect, develop, and test new tools, particularly search. These tools support the companys core mission, which is to analyze very large (on the order of millions) document sets, in order to identify documents relevant to a particular legal case. 2005-2007.

Entrieva. Unstructured document management applications. Languages & Operating Systems: Java, C++, Windows, UNIX. Lead project to maintain and upgrade categorization software central to solutions provided by Entrieva. Architected new solutions to augment product portfolio in order to expand Entrieva's services and increase its competitiveness, requiring a complete understanding of the company's proprietary language processing algorithms and market position. 2003-2005.

AdaptiveLava. Peer-to-peer artificial intelligence. Language & Operating Systems: Java, Windows, Mac OS. Chief architect of application in ongoing project to merge peer-to-peer functionality with artificial intelligence/natural language systems in an enterprise environment, based on open source code. By utilizing search and retrieval algorithms, the application makes previously inaccessible files on individual PCs accessible and available to many users within an enterprise or knowledge community, rather than only files specifically pushed to servers. This enables the enterprise or community to leverage existing intellectual property assets to a level not before possible. 2001-2003.

Ask Jeeves. Classifier project. Language & Operating System: C++/Windows 2000. Lead on project to design and implement engine of the Comprecorp Classifier, intended to classify e-mail and other such free-text documents of arbitrary length, according to user-specified categories. The user does not have to tell the system what rules are used to put a document in a particular category. It learns by example from looking at documents already in categories. Potential uses of such a system go beyond e-mail classification, to a wide variety large-scale document management and data mining applications. 2001.

Jeeves automation project. Language & Operating System: C++/Windows NT. Lead on project to improve accuracy and lower cost for Jeeves question-answering system. In the original system, creating and maintaining a knowledgebase of questions and answers was too labor intensive, and too costly, to encourage the use of the product by smaller businesses, particularly in the face of increasing competition from other question-answering products. As project lead, I identified bottlenecks in the creation of knowledgebases that were amenable to adaptive automation, created design specifications, and lead a team in writing code to implement those changes. I presented both method and results to company members through meetings and on-line publications, and worked with in-house customers to refine the prototype's usability. The result was comparable prototype knowledgebases whose creation and maintenance required significantly less human effort and cost less. 1999 - 2000.

CMU/UC San Diego. Neural network simulator. Language & Operating System: C++/MacOS. Sole developer and maintainer, simulX, general neural network simulator for desktop platforms. This application is designed for a range of users, from beginners in neural networks to advanced neural network researchers, using a variety of different network architectures that can be combined on demand. 1996 - 1999.

Publications

Blackwell, A., Bates, E., & Fisher, D. (1996). The time course of grammaticality judgment. Language and Cognitive Processes, 11(4), 337-406.

Blackwell, A.W. & Bates, E. (1995). Inducing agrammatic profiles in normals: Evidence for the selective vulnerability of morphology under cognitive resource limitation. Journal of Cognitive Neuroscience, 7, 228-257.

Blackwell, A.W. (1995) Artificial Languages/Virtual Brains. Unpublished dissertation.

[publications & projects continued]

Education

Ph.D., University of California, San Diego, 1995: Cognitive Science and Psychology.

A.B., Brown University, 1987: Honors Cognitive Science and Honors Creative Writing.