LeQua 2022: Learning to Quantify
The aim of LeQua 2022 (the 1st edition of the CLEF “Learning to Quantify” lab) is to allow the comparative evaluation of methods for “learning to quantify” in textual datasets, i.e., methods for training predictors of the relative frequencies of the classes of interest in sets of unlabelled (textual) documents. These predictors (called “quantifiers”) are required to issue predictions for several such sets, some of them characterized by class frequencies radically different from the ones of the training set. For a detailed description of this lab you are welcome to download the paper Andrea Esuli, Alejandro Moreo, Fabrizio Sebastiani: LeQua@CLEF2022: Learning to Quantify. Proceedings of the 44th European Conference on Information Retrieval (ECIR 2022), Stavanger, NO, pp. 374-381.
News!
- 7 Aug 2022: The LeQua 2022 session at CLEF 2022 in Bologna, Italy will take place on Wednesday, September 7, from 15:30 to 18:50; all times are CEST.
- 30 May 2022: We are delighted to announce that the LeQua 2022 session at CLEF 2022 in Bologna will host a keynote talk by George Forman (Amazon Research)
- 28 May 2022: The submission period for participants’ papers is now over; thanks to the teams who have submitted their papers!
- 11 May 2022: The submission period is now over; thanks to the teams who have submitted their runs! The test set (with labels) is now public and accessible via Zenodo!
- 22 April 2022: The test set (with labels omitted) is now public and accessible via Zenodo! You can now submit your results via CodaLab!
- 1st Dec 2021: The dataset (training and development sets) is now public and accessible via Zenodo
- 1st Dec 2021: The format checker and evaluation script, along with other useful functions and further guidelines, are public and accessible via GitHub.
- 1st Dec 2021: The Google discussion group has been created! If you plan to participate (and we very much hope so), visit https://groups.google.com/g/lequa2022 and request to become a member now!
- 15 Nov 2021: Registrations are open! (until 22 Apr 2022)
Useful links
If you are interested in research on learning to quantify, you might want to check the proceedings of the 1st International Workshop on Learning to Quantify (LQ 2021), which took place on November 1 and November 5, 2021. A report of that workshop has also been published as Juan José del Coz, Pablo González, Alejandro Moreo, and Fabrizio Sebastiani. Report on the 1st International Workshop on Learning to Quantify (LQ 2021). SIGKDD Explorations 24(1):49–51, 2022.
For a survey of research on learning to quantify up to 2017, see Pablo González, Alberto Castaño, Nitesh V. Chawla, Juan José del Coz: A Review on Quantification Learning. ACM Computing Surveys 50(5): 74:1-74:40 (2017); for more recent work, check the proceedings of LQ 2021.
Register you and your team for participating to LeQua 2022 (and other CLEF 2022 labs too) on the CLEF 2022 Lab registration page.
Follow us on Twitter: @LeQua2022
LeQua 2022 is supported by the SoBigData++ project, funded by the European Commission (Grant 871042) under the H2020 Programme INFRAIA-2019-1, and by the AI4Media project, funded by the European Commission (Grant 951911) under the H2020 Programme ICT-48-2020. The organizers’ opinions do not necessarily reflect those of the European Commission.