Pedagogically Aligned Objectives Create Reliable Automatic Cloze Tests

Brian Ondov, Kush Attal, Dina Demner-Fushman


Abstract
The cloze training objective of Masked Language Models makes them a natural choice for generating plausible distractors for human cloze questions. However, distractors must also be both distinct and incorrect, neither of which is directly addressed by existing neural methods. Evaluation of recent models has also relied largely on automated metrics, which cannot demonstrate the reliability or validity of human comprehension tests. In this work, we first formulate the pedagogically motivated objectives of plausibility, incorrectness, and distinctiveness in terms of conditional distributions from language models. Second, we present an unsupervised, interpretable method that uses these objectives to jointly optimize sets of distractors. Third, we test the reliability and validity of the resulting cloze tests compared to other methods with human participants. We find our method has stronger correlation with teacher-created comprehension tests than the state-of-the-art neural method and is more internally consistent. Our implementation is freely available and can quickly create a multiple choice cloze test from any given passage.
Anthology ID:
2024.naacl-long.220
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3961–3972
Language:
URL:
https://aclanthology.org/2024.naacl-long.220
DOI:
Bibkey:
Cite (ACL):
Brian Ondov, Kush Attal, and Dina Demner-Fushman. 2024. Pedagogically Aligned Objectives Create Reliable Automatic Cloze Tests. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 3961–3972, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Pedagogically Aligned Objectives Create Reliable Automatic Cloze Tests (Ondov et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.220.pdf
Copyright:
 2024.naacl-long.220.copyright.pdf