I am Alex (Oleksandr) Polozov, a third-year graduate student in the Computer Science & Engineering Department at the University of Washington. My advisors are Sumit Gulwani and Zoran Popović. I work on applying formal methods of programming languages and program synthesis to aid STEM education and end-user data manipulation.
I received my B.S. in System Analysis with honors from the National Technical University of Ukraine "Kyiv Polytechnic Institute" in 2012.
My interests lie in the applications of formal methods (software engineering, program synthesis, answer set programming) for math/programming education and end-user data manipulation. Currently, I am working on the following projects:
- FlashMeta, a meta-framework for program synthesis in domain-specific languages from inductive specifications (input-output examples)
- Personalized mathematical word problem generation using answer set programming
- LaSE: end-user query languages for semi-structured data extraction
Personalized Mathematical Word Problem Generation
Oleksandr Polozov, Eleanor O'Rourke, Adam M. Smith, Luke Zettlemoyer, Sumit Gulwani, Zoran Popović
[abstract] [project info] [pdf]
Word problems are an established technique for teaching mathematical modeling skills in K-12 education. However, many students find word problems unconnected to their lives, artificial, and uninteresting. Most students find them much more difficult than the corresponding symbolic representations. To account for this phenomenon, an ideal pedagogy might involve an individually crafted progression of unique word problems that form a personalized plot.
We propose a novel technique for automatic generation of personalized word problems. In our system, word problems are generated from general specifications using answer-set programming (ASP). The specifications include tutor requirements (properties of a mathematical model), and student requirements (personalization, characters, setting). Our system takes a logical encoding of the specification, synthesizes a word problem narrative and its mathematical model as a labeled logical plot graph, and realizes the problem in natural language. Human judges found our problems as solvable as the textbook problems, with a slightly more artificial language.
LaSEWeb: Automating Search Strategies over Semi-structured Web Data
Oleksandr Polozov, Sumit Gulwani
[abstract] [project info] [pdf] [slides]
We show how to programmatically model processes that humans use when extracting answers to queries (e.g., "Who invented typewriter?", "List of Washington national parks") from semi-structured Web pages returned by a search engine. This modeling enables various applications including automating repetitive search tasks, and helping search engine developers design micro-segments of factoid questions.
We describe the design and implementation of a domain-specific language that enables extracting data from a webpage based on its structure, visual layout, and linguistic patterns. We also describe an algorithm to rank multiple answers extracted from multiple webpages.
On 100,000+ queries (across 7 micro-segments) obtained from Bing logs, our system LaSEWeb answered queries with an average recall of 71%. Also, the desired answer(s) were present in top-3 suggestions for 95%+ cases.