工作经历 Software Engineer Google 2013 年 5 月 – 至今 (3 年 1 个月)瑞士 (开放)3 门课程 PhD student University of Amsterdam 2012 年 9 月 – 至今 (3 年 9 个月)荷兰 阿姆斯特丹地区 Applied Researcher Yandex 2012 年 9 月 – 2013 年 4 月 (8 个月)俄罗斯联邦 莫斯科 Research on user behavior, aggregated search, click models. (开放)4 门课程 Software Developer Yandex 2010 年 9 月 – 2012 年 8 月 (2 年)俄罗斯联邦 莫斯科 Improve Web Ranking (开放)1 个项目 (开放)4 门课程 (开放)2 封推荐信 Kirill Pavlov Kirill Pavlov (Hiring Data Scientists) Evangelist of Data Mining Alexandr has strength technical background, especially in python, С++, and algorithms as well. He is one of the persons who...查看 Andrey Styskin Andrey Styskin Head of Search Quality at Yandex Alexander is industrious, responsible. Interested in releted fields and technologies. Ambitious. Able to find compromises...查看 Teaching Assistant Moscow Institute of Physics and Technology (State University) 2011 年 1 月 – 2012 年 6 月 (1 年 6 个月) * practical classes for "Operating Systems and Computer Architecture" course; * lecture course titled "Python programming language" Intern EPFL 2011 年 10 月 – 2012 年 1 月 (4 个月)Lausanne Area, Switzerland Participated in developing a scientist-generated on-line knowledge base (see sciencewise.info) Software Developer Intern Yandex 2009 年 12 月 – 2010 年 8 月 (9 个月)俄罗斯联邦 莫斯科 Developed a toy search engine for Wikipedia using c++ and Boost (from scratch). Personal Teacher Vash Repetitor (repetitors.info) 2006 年 12 月 – 2010 年 6 月 (3 年 7 个月) Personal lessons in maths, physics, informatics (school and university students). 资格认证 Probabilistic Graphical Models(链接)Coursera Coursera 开始日期: 2012 年 12 月 Natural Language Processing(链接)Coursera Coursera 开始日期: 2012 年 5 月 Algorithms: Design and Analysis, Part 1(链接)Coursera Coursera 开始日期: 2012 年 4 月 Functional Programming Principles in Scala(链接)Coursera Coursera 开始日期: 2012 年 11 月 出版作品 Effective protocols for low-distance file synchronization [rus](链接) arXiv preprint arXiv:1102.4712 2011 年 2 月 23 日 Suppose that we have two similar files stored on different computers. We need to send the file from the first computer to the second one trying to minimize the number of bits transmitted. This article presents a survey of results known for this communication complexity problem in the case when files are "similar" in the sense of Hamming distance. We mainly systematize earlier results obtained by...展开 Potential good abandonment prediction(链接) WWW 2012 2012 年 4 月 16 日 Abandonment rate is one of the most broadly used online user satisfaction metrics. In this paper we discuss the notion of potential good abandonment, i.e. queries that may potentially result in user satisfaction without the need to click on search results (if search engine result page contains enough details to satisfy the user information need). We show, that we can train a classifier which is...展开 共 2 位作者 Aleksandr Chuklin Aleksandr Chuklin Software Engineer at Google Pavel Serdyukov Pavel Serdyukov Researcher at Yandex Good abandonments in factoid queries(链接) WWW 2012 2012 年 4 月 16 日 It is often considered that high abandonment rate corresponds to poor IR system performance. However several studies suggested that there are so called good abandonments, i.e. situations when search engine result page (SERP) contains enough details to satisfy the user information need without necessity to click on search results. In those papers only editorial metrics of SERP were used, and one...展开 共 2 位作者 Aleksandr Chuklin Aleksandr Chuklin Software Engineer at Google Pavel Serdyukov Pavel Serdyukov Researcher at Yandex How Query Extensions Reflect Search Result Abandonments(链接) SIGIR 2012 2012 年 8 月 12 日 It is often considered that high abandonment rate corresponds to poor IR system performance. However several studies suggested that there are so called good abandonments, i.e. situations when search engine result page contains enough details to satisfy the user information need without necessity to click on search results. In this work we propose to look at query extensions. We see that an...展开 共 2 位作者 Aleksandr Chuklin Aleksandr Chuklin Software Engineer at Google Pavel Serdyukov Pavel Serdyukov Researcher at Yandex Adult query classification for web search and recommendation(链接) Search and Exploration of X-rated Information (WSDM'13 Workshop Proceedings) 2013 年 2 月 5 日 The Internet is a rich source of various adult content. Though, the web search engine must provide the user with X-rated content only in case the user’s query has an adult intent. In this paper we suggest a three-class distribution of search queries with respect to their adultness and present an adult content classificator based on language models. 共 2 位作者 Aleksandr Chuklin Aleksandr Chuklin Software Engineer at Google Alisa Lavrentyeva Alisa Lavrentyeva Team Lead – Yandex Using Intent Information to Model User Behavior in Diversified Search(链接) ECIR 2013 2013 A result page of a modern commercial search engine often contains documents of different types targeted to satisfy different user intents (news, blogs, multimedia). When evaluating system performance and making design decisions we need to better understand user behavior on such result pages. To address this problem various click models have previously been proposed. In this paper we focus on...展开 共 3 位作者 Aleksandr Chuklin Aleksandr Chuklin Software Engineer at Google Pavel Serdyukov Pavel Serdyukov Researcher at Yandex Maarten de Rijke Maarten de Rijke Professor of Computer Science, University of Amsterdam Click Model-Based Information Retrieval Metrics(链接) SIGIR 2013 2013 In recent years many models have been proposed that are aimed at predicting clicks of web search users. In addition, some information retrieval evaluation metrics have been built on top of a user model. In this paper we bring these two directions together and propose a common approach to converting any click model into an evaluation metric. We then put the resulting model-based metrics as well as...展开 共 3 位作者 Aleksandr Chuklin Aleksandr Chuklin Software Engineer at Google Pavel Serdyukov Pavel Serdyukov Researcher at Yandex Maarten de Rijke Maarten de Rijke Professor of Computer Science, University of Amsterdam Evaluating Aggregated Search Using Interleaving(链接) CIKM 2013 2013 A result page of a modern web search engine is often much more complicated than a simple list of “ten blue links”. In particular, a search engine may combine results from different sources (e.g., Web, News, and Images), and display these as grouped results to provide a better user experience. Such a system is called an aggregated or federated search system. Because search engines evolve over time...展开 (开放)共 5 位作者: Aleksandr Chuklin Aleksandr Chuklin Software Engineer at Google Anne Schuth Anne Schuth Data Scientist at Blendle Katja Hofmann Katja Hofmann Researcher at Microsoft Pavel Serdyukov Pavel Serdyukov Researcher at Yandex Modeling Clicks Beyond the First Result Page(链接) CIKM 2013 2013 Most modern web search engines yield a list of documents of a fixed length (usually 10) in response to a user query. The next ten search results are usually available in one click. These documents either replace the current result page or are appended to the end. Hence, in order to examine more documents than the first 10 the user needs to explicitly express her intention. Although...展开 共 3 位作者 Aleksandr Chuklin Aleksandr Chuklin Software Engineer at Google Pavel Serdyukov Pavel Serdyukov Researcher at Yandex Maarten de Rijke Maarten de Rijke Professor of Computer Science, University of A