Ferro N., Fuhr N., Grefenstette G., Konstan J. A., Castells P., Daly E. M., Declerck T., Ekstrand M. D., Geyer W., Gonzalo J., Kuflik T., Lind'En K., Magnini B., Nie J. Y., Perego R., Shapira B., Soboroff I., Tintarev N., Verspoor K., Willemsen M. C., Zobel J.
Evaluation Simulation User interaction Computer Science Information Systems Formal models general works 000 Computer science knowledge
We describe the state-of-the-art in performance modeling and prediction for Information Retrieval (IR), Natural Language Processing (NLP) and Recommender Systems (RecSys) along with its shortcomings and strengths. We present a framework for further research, identifying five major problem areas: understanding measures, performance analysis, making underlying assumptions explicit, identifying application features determining performance, and the development of predic- tion models describing the relationship between assumptions, features and resulting performance
Source: Dagstuhl manifestos 7 (2018): 96–139. doi:10.4230/DagMan.7.1.96
Publisher: Schloss Dagstuhl, Leibniz-Zentrum für Informatik GmbH, Wadern , Germania
@article{oai:it.cnr:prodotti:416340, title = {From Evaluating to Forecasting Performance: How to Turn Information Retrieval, Natural Language Processing and Recommender Systems into Predictive Sciences (Dagstuhl Perspectives Workshop 17442)}, author = {Ferro N. and Fuhr N. and Grefenstette G. and Konstan J. A. and Castells P. and Daly E. M. and Declerck T. and Ekstrand M. D. and Geyer W. and Gonzalo J. and Kuflik T. and Lind'En K. and Magnini B. and Nie J. Y. and Perego R. and Shapira B. and Soboroff I. and Tintarev N. and Verspoor K. and Willemsen M. C. and Zobel J.}, publisher = {Schloss Dagstuhl, Leibniz-Zentrum für Informatik GmbH, Wadern , Germania}, doi = {10.4230/dagman.7.1.96}, journal = {Dagstuhl manifestos}, volume = {7}, pages = {96–139}, year = {2018} }