Close this search box.

Talk: Better Representations for Search Tasks by Jamie Callan

Jamie Callan, Professor at the Language Technologies Institute in Carnegie Mellon’s School of Computer Science, will be giving a keynote lecture under the scope of the ECIR 2020 – 42nd European Conference on Information Retrieval. Jamie Callan has been collaborating extensively with the CMU Portugal as a PI of projects and adviser to dual degree students. Currently, Jamie is the PI at CMU of the project GoLocal coordinated in Portugal by João Magalhães (FCTUNL).

ECIR2020 is now an online event that will be broadcasted on the conference’s YouTube channel. 

2:00pm Lisbon | 9:00 Washington DC | 21:00 Beijing


Neural models are having a major impact on Information Retrieval, much as they have had recently on other language technologies.  Neural language models and continuous term representations provide new and more effective paths to overcoming vocabulary mismatch, probability estimation, and other core problems in Information Retrieval.  Some classic Natural Language Processing tasks are now treated as text similarity problems, and techniques developed for NLP are being applied to classic IR problems, which reduces some of the past differences between IR and NLP.  Everything uses machine learning. This technology shift is a good time to think about what is unique and distinct about Information Retrieval as a field compared to neighboring fields.

From its earliest days, Information Retrieval has studied document collections, information seekers, and information-seeking tasks.  These topics are embedded deeply in our experimental methodology and how we think about research problems. Neighboring fields focus more attention and computational effort on understanding individual documents, and less on how individual documents should be understood in the context of specific people, tasks, and collections.  

This talk describes several recent research activities at CMU’s Language Technologies Institute.  Although each has a different focus, the unifying theme is using knowledge of the search task, context, or corpus to develop more effective representations and models.  We find that neural techniques offer new tools for understanding and modeling these core elements of search, in some cases reinvigorating research in stable areas and challenging old assumptions, but do not reduce their importance.

Jamie Callan is a Professor at the Language Technologies Institute in Carnegie Mellon’s School of Computer Science.  His recent research develops search engine architectures, neural search algorithms, use of semi-structured knowledge for open-domain search, conversational information seeking, and large-scale distributed search.  He has been a Chair and Treasurer of SIGIR, a co-Editor-in-Chief of Foundations and Trends in Information Retrieval, and an Editor-in-Chief of ACM’s Transactions on Information Systems (TOIS).

Start date

Apr. 16, 2020

2:00 pm

End Date

Apr. 16, 2020

3:00 pm