TY - GEN
T1 - ILDAE
T2 - 60th Annual Meeting of the Association for Computational Linguistics, ACL 2022
AU - Varshney, Neeraj
AU - Mishra, Swaroop
AU - Baral, Chitta
N1 - Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022
Y1 - 2022
N2 - Knowledge of difficulty level of questions helps a teacher in several ways, such as estimating students' potential quickly by asking carefully selected questions and improving quality of examination by modifying trivial and hard questions. Can we extract such benefits of instance difficulty in Natural Language Processing? To this end, we conduct Instance-Level Difficulty Analysis of Evaluation data (ILDAE) in a large-scale setup of 23 datasets and demonstrate its five novel applications: 1) conducting efficient-yet-accurate evaluations with fewer instances saving computational cost and time, 2) improving quality of existing evaluation datasets by repairing erroneous and trivial instances, 3) selecting the best model based on application requirements, 4) analyzing dataset characteristics for guiding future data creation, 5) estimating Out-of-Domain performance reliably. Comprehensive experiments for these applications lead to several interesting results, such as evaluation using just 5% instances (selected via ILDAE) achieves as high as 0.93 Kendall correlation with evaluation using complete dataset and computing weighted accuracy using difficulty scores leads to 5.2% higher correlation with Out-of-Domain performance. We release the difficulty scores and hope our work will encourage research in this important yet understudied field of leveraging instance difficulty in evaluations.
AB - Knowledge of difficulty level of questions helps a teacher in several ways, such as estimating students' potential quickly by asking carefully selected questions and improving quality of examination by modifying trivial and hard questions. Can we extract such benefits of instance difficulty in Natural Language Processing? To this end, we conduct Instance-Level Difficulty Analysis of Evaluation data (ILDAE) in a large-scale setup of 23 datasets and demonstrate its five novel applications: 1) conducting efficient-yet-accurate evaluations with fewer instances saving computational cost and time, 2) improving quality of existing evaluation datasets by repairing erroneous and trivial instances, 3) selecting the best model based on application requirements, 4) analyzing dataset characteristics for guiding future data creation, 5) estimating Out-of-Domain performance reliably. Comprehensive experiments for these applications lead to several interesting results, such as evaluation using just 5% instances (selected via ILDAE) achieves as high as 0.93 Kendall correlation with evaluation using complete dataset and computing weighted accuracy using difficulty scores leads to 5.2% higher correlation with Out-of-Domain performance. We release the difficulty scores and hope our work will encourage research in this important yet understudied field of leveraging instance difficulty in evaluations.
UR - http://www.scopus.com/inward/record.url?scp=85137568211&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85137568211&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85137568211
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 3412
EP - 3425
BT - ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
A2 - Muresan, Smaranda
A2 - Nakov, Preslav
A2 - Villavicencio, Aline
PB - Association for Computational Linguistics (ACL)
Y2 - 22 May 2022 through 27 May 2022
ER -