On IR Experimentation
Decanato - Facoltà di scienze informatiche
Data d'inizio: 29 Aprile 2013
Data di fine: 30 Aprile 2013
The Faculty of Informatics is pleased to announce a seminar given by Evangelos Kanoulas
DATE: Monday, April 29th 2013
PLACE: USI Lugano Campus, room SI-008, Informatics building (Via G. Buffi 13)
TIME: 10.30
ABSTRACT:
Information Retrieval (IR) is the study of methods for organizing and searching large sets of heterogeneous, unstructured or semi-structured data. The growth of the Web and the consequent need to organize and search a vast amount of information has demonstrated the importance of IR, while the success of web search engines has proven that IR can provide eminently valuable tools to manage large amounts of data. The range of tasks and information collections IR systems are applied to is ever growing. However, the ability of researchers and developers to build high quality searching systems for new environments is not keeping up with the growth in potential application areas. The key reason for this failing is the profound lack of testing resources that capture the unique and complex environments different retrieval systems are deployed in. The cost of building test resources is prohibitively expensive. Consequently, researchers are unable to assess the effectiveness of new ideas in such environments and search engine vendors struggle to tune their systems to the particular needs of their customers. In this talk I will discuss my work on a new evaluation paradigm for search, which establishes an efficient and reliable testing methodology, and extend the current evaluation paradigm to incorporate additional information about the different retrieval scenarios and users activities.
BIO:
Evangelos Kanoulas is a Research Scientist in the group of text summarization and natural language understanding at Google Research, Zurich. His research interests lie in the fields of Information Retrieval and Natural Language Processing. His work at Google has focused on entity-centric summarization of user generated content on the Web around memorable events and aggregation of propositional content. This is part of the massive shift that Google has introduced to the search paradigm moving "from strings to things". He is also involved in a European project on "Policy formulation and validation through non-moderated crowd-sourcing" (NOMAD FP7-288513).
Evangelos received his PhD degree from Northeastern University, Boston, and worked for two years as a Marie Curie fellow at the University of Sheffield. During the years of his fellowship he also held a visiting researcher position at Microsoft Research Cambridge, working with Bing research scientists, and at University College London. During his PhD, he focused on the filed of Information Retrieval and in particular on constructing efficient and reliable evaluation benchmarks (collections) and on developing effectiveness metrics for the evaluation of retrieval systems. He contributed writing an NSF grant proposal which has been funded with $488,723 (NSF IIS-1017903) and Marie Curie grant proposal which got awarded with 172,241 Euros (FP7-PEOPLE-2009-IFF - No 254562). With others he co-ordinated the Million Query track at TREC, funded by the National Institute of Standards and Technologies, USA, he proposed and organized the Session Track and he has extensively published in top-tier conferences in information retrieval, such as SIGIR, CIKM and ECIR.
HOST: Prof. Fabio Crestani