Category Archives: Information Retrieval

  • 0

讲座信息:TextScope: Enhance Human Perception via Intelligent Text Retrieval and Mining

时间: 12月27日 周四 下午10:00-12:00
地点:信息楼123会议室
题目: TextScope: Enhance Human Perception via Intelligent Text Retrieval and Mining
报告人: Professor ChengXiang Zhai

ABSTRACT:

Recent years have seen a dramatic growth of natural language text data, including, e.g., web pages, news articles, scientific literature, emails, enterprise documents, and social media such as blog articles, forum posts, product reviews, and tweets. Text data contain all kinds of knowledge about the world and human opinions and preferences, thus offering great opportunities for mining actionable knowledge from vast amounts of text data (“big text data”) to support user tasks and optimize decision making in all application domains. However, computers cannot yet accurately understand unrestricted natural language; as such, how to analyze and mine big text data effectively and efficiently is a difficult challenge, and involving humans in a loop of interactive retrieval and mining of text data is essential. In this talk, I will present the vision of TextScope, an interactive software tool to enable users to perform intelligent information retrieval and text analysis in a unified task-support framework. Just as a microscope allows us to see things in the “micro world,” and a telescope allows us to see things far away, the envisioned TextScope would allow us to “see” useful hidden knowledge buried in large amounts of text data that would otherwise be unknown to us. As examples of techniques that can be used to build a TextScope, I will present some of our recent work on formal models for optimizing interactive information retrieval and general algorithms for analyzing text and non-text data jointly to discover interesting patterns and knowledge. At the end, I will discuss the major challenges in developing a TextScope and some important directions for future research.

BIO:

ChengXiang Zhai is a Donald Biggar Willett Professor in Engineering of the Department of Computer Science at the University of Illinois at Urbana-Champaign (UIUC), where he is also affiliated with the Carl R. Woese Institute for Genomic Biology, Department of Statistics, and School of Information Sciences. He received a Ph.D. in Computer Science from Nanjing University in 1990, and a Ph.D. in Language and Information Technologies from Carnegie Mellon University in 2002. He worked at Clairvoyance Corp. as a Research Scientist and a Senior Research Scientist from 1997 to 2000. His research interests are in the general area of intelligent information systems, including specifically information retrieval, data mining, and their applications in many areas especially biomedical and health informatics, and intelligent education systems.  He has published over 300 papers in these areas with high citations, and a textbook on text data management and analysis, which is used worldwide by many learners of the two MOOCs that he offered on Coursera. He served as Associate Editors for major journals in multiple areas including information retrieval (ACM TOIS, IPM), data mining (ACM TKDD), and medical informatics (BMC MIDM), and as Program Co-Chairs of ACM SIGIR 2009 and WWW 2015. He is an ACM Fellow and received a number of awards, including ACM SIGIR Test of Time Paper Award (three times), the 2004 Presidential Early Career Award for Scientists and Engineers (PECASE), an Alfred P. Sloan Research Fellowship, IBM Faculty Award, HP Innovation Research Award, and UIUC Campus Award for Excellence in Graduate Student Mentoring. More information about him and his work can be found from his homepage at http://czhai.cs.illinois.edu/.

 


  • 0

讲座信息:On the Generalizability of Results from Interactive Information Retrieval Research

时间: 10月16日 周二 上午9:30-10:30
地点:信息楼123会议室
题目: On the Generalizability of Results from Interactive Information Retrieval Research
报告人:  Professor Diane Kelly

ABSTRACT:

The idealized model of conducting empirical research starts with a theory, which is then used to derive one or more hypotheses, which are then evaluated using an appropriate method. In this idealized model, statistical methods are used to evaluate the hypothesis. Very often, especially in fields that do not have a strong tradition of theory-building and testing, such as interactive information retrieval, researchers deduce hypotheses from past empirical research reports. But what if these research reports cannot be trusted or generalized?  What if the findings are strictly a function of the time at which the studies were conducted, or the environments in which they were conducted? What if the measures themselves produce findings that are unlikely to be observed in another study context even when the same instruments are used? Concerns about the generalizability, replicability and reproducibility of research is of growing interest to those working in many research specialties, including information retrieval.  This talk focuses on one aspect of generalizability – the extent to which the findings from one research study can be used to make predictions about what will happen in another research study – and  considers how different community practices with respect replicability and reproducibility might help us address result generalizability so we can begin to construct more lasting and useful theories about information search behaviors.

BIO:

Diane Kelly is Professor and Director of the School of Information Sciences at the University of Tennessee.  Prior to this, she was a professor at the University of North Carolina at Chapel Hill. Her research and teaching interests are in interactive information search and retrieval, information search behavior, and research methods. She is the recipient of the 2014 ASIST Research Award, the 2013 British Computer Society’s IRSG Karen Spärck Jones Award, the 2009 ASIST/Thomson Reuters Outstanding Information Science Teacher Award and the 2007 SILS Outstanding Teacher of the Year Award.  She is the current chair of ACM SIGIR, associate editor of ACM Transactions on Information Systems and serves on the editorial boards of several journals including, Information Processing & Management, and Information Retrieval Journal.  Kelly received a PhD, MLS and a graduate certificate in cognitive science from Rutgers University and an undergraduate degree from the University of Alabama.