Ken Samuel

Lafayette, LA *****

703-***-**** Cell

ad2bz8@r.postjobfree.com

www.Linkedin.com/in/ken-samuel-78b9936b/

Data Entry

I have been entering data into computers since I was a child, and I'm very good at it. Work Experience

Feb 2022 to May 2022 Tutor – The Princeton Review – Frederick, Maryland

• I taught students algebra, Microsoft Excel, and Computer Science.

Jun 2021 to Aug 2021 AI/ML Engineer – The Rigil Corporation – Chantilly, Virginia

• I did research within the domain of artificial intelligence. May 2013 to Jun 2021 Senior Researcher – Intelligent Automation, Incorporated – Rockville, Maryland

• I did research within the domain of artificial intelligence. See page 2 for more details.

Jun 1999 to Apr 2013 Senior Artificial Intelligence Engineer – The MITRE Corporation – McLean, Virginia

• I completed a wide variety of different information technology tasks, most of which required research in the domain of artificial intelligence. See page 2 for more details.

Jan 1999 to May 1999 Teacher – The University of Delaware – Newark, Delaware

• I took full responsibility for teaching an undergraduate Computer Science course, preparing and presenting lectures, creating and grading homework assignments, projects, lab assignments, and exams, etc.

Education

o Doctor of Philosophy: Computer and Information Sciences, specializing in Data Mining and Computational Linguistics, The University of Delaware (12/1994 – 12/2000)

o Master of Science: Computer Science, The University of Texas at Austin (9/1992 – 12/1994)

o Bachelor of Science: Major in Computer Science and Mathematics, Minor in Physics and Philosophy, Rutgers University (9/1988 – 5/1992) Key projects include

o For the “Database Assurance” research project, I discovered Cross-Feature Analysis, an unsupervised machine learning algorithm, implemented a large system in Java integrating that algorithm with the Weka machine learning toolkit, and improved and extended that system. When applied to a database cyber security task as an anomaly detection algorithm, the system was wildly successful, detecting attacks with scores as high as specificity = 99.9% and recall = 100%. [Samuel et al., 2010]

o For my Ph.D. work, I applied Transformation-Based Learning, a supervised machine learning algorithm, to Dialog Act Tagging, a discourse-level natural language processing problem. I implemented a system in Lisp and improved and extended it, achieving an accuracy of 77.44% on this very difficult task. [Samuel, 2001]

o For the “Data Discovery using Digests” research project, I implemented a system in Python that analyzed unstructured text by applying natural language processing techniques such as expanding acronyms and abbreviations, removing stop words, finding synonyms, and stemming words. The system output was a list of terms that could be used to search through the data. [Mork et al., 2010]

o For the “Semantic Web Rules” research project, I implemented a system in Prolog that logically derived a set of facts from an OWL ontology and SWRL rules. Prior work had claimed this was impossible, listing a number of prohibitive problems, but I invented novel solutions for several of those problems. [Samuel et al., 2008] o For the “DIAD (Data Ingestion, Analytics, and Delivery)” research project, I enhanced the information extraction capabilities of the GATE (General Architecture for Text Engineering) system, by improving its entity extraction code, enabling it to extract new entity types, and adding relation extraction and event extraction capabilities to it. After several years of writing Jape programs in GATE, I now consider myself an expert of this complex toolkit.

o For the “DataHub” project, I implemented, in Java, the Wanderlust approach for relation extraction, improved it, and evaluated it. When compared to JET (Java Extraction Toolkit) on the Wikipedia Relation Extraction Data v1.0, it surpassed that state-of-the-art system on both recall and precision. [Samuel at al., 2018]

Skills: Software development, documentating code, application testing, proofreading, teaching, learning, presenting briefings, research, artificial intelligence, machine learning, natural language processing, data analysis, data mining, computational linguistics, data analytics, information semantics, knowledge discovery, information semantics, information extraction, information retrieval, machine translation, Java, Perl, C++, Python, JavaScript, Lisp, Prolog, Matlab, SQL, HTML, CSS, C, R, Assembly, Weka, NLTK, GATE, JET, Microsoft 365, Microsoft Office, Eclipse, Everything, emacs, Adobe Acrobat, Windows 10/7/XP/2000/NT/98/95, Classic Mac OS, Mac OS, UNIX, Linux, ...