1.    讲座题目：Survey of Text Summarization Techniques

摘要：

Text summarization is the task of automatically generating a short and comprehensive description for a large text of a collection of texts. Text summarization has become an important research area due to the proliferation of large digital text collections, such as blogs or news, that produce a demand for quick automatic summarizations. Moreover, the increasing trend of crossborder globalization and acculturation requires text summarization techniques to work equally well for multiple languages. Generally speaking, all text summarization methods can be divided into supervised or unsupervised. Supervised tasks require training data for learning a model that is used later for decision making.

In this talk, we discuss different types of text summarization, such as extractive, abstractive and compressive summarization, general and query-based summarization, single and multi-text summarization. We survey up-to-date methods of text summarization, both supervised and unsupervised, focusing on those specially suitable for multilingual domain.

主讲人介绍：

Marina Litvak has obtained a Ph.D. in Information Systems Engineering from Ben-Gurion University of the Negev. She is currently a faculty member at Department of Software Engineering of Shamoon College of Engineering in Beer Sheba, Israel. Her research interests include information retrieval, text mining, automated summarization, and social media analysis. She is a member of the Association for Computational Linguistics. Marina is a co-designer of the MUSE summarizer and the MUSEEC system, which are known summarization systems in the multilingual text summarization. She serves as a program committee member and a reviewer in the summarization and multilinguality tracks in the ACL sponsored conferences. Marina is a co-organizer of the MultiLing contest since 2011.

2.讲座题目：Event Detection and Analysis in Twitter

摘要：

Data analysis in social media is a broad and well-addressed research topic, but the characteristics and sheer volume of microblog messages (e.g., Twitter or Weibo) with high amounts of noise in them make it a difficult task. Messages reporting real-life events are usually overwhelmed by a flood of meaningless information.

In this talk we give a definition of what comprises an event in social media and what types of events can be defined there. We will also present in details our system for real-life event detection and analysis in Twitter named TWIST.

For providing high-quality summaries with clean and meaningful content, TWIST analyzes

external sources for detected events, which it accomplishes by retrieving links and extracting the main tweets describing those events. Then, all detected events are analyzed by their sentiment distribution over a world map, and visualized in the resolution of countries. This feature enables the TWIST user to see whether, and if so, how the geolocation of Twitter users affects their opinions, and how the sentiments and opinions regarding the same event can be different over different countries.

主讲人介绍：

Natalia Vanetik is a currently a faculty member at Department of Software Engineering of Shamoon Academic College of Engineering in Beer Sheva, Israel. Her main field of interest is Text Analysis, focusing on multilingual Text Summarization, and unsupervised optimization methods.  She is the author of multiple scientific publications in international peer-reviewed conferences and refereed journals. She has served on the program committee for several international conferences. She has obtained her PhD in Computer Science from Ben-Gurion University of the Negev in 2009 in the field of Graph Mining and Combinatorial Optimization.  Since 2010, she has been involved in teaching activities at Shamoon Academic College of Engineering, more specifically she teaches multiple courses at the undergraduate degree in Software Engineering and the master’s degree in Software Engineering, with focus on courses in fields of Databases, Algorithms and Data Mining.

该讲座为前沿讲座，欢迎全校师生踊跃参加。