Text embeddings recover 57-63% of the reliable variance in exam-item difficulty, and apparent differences in predictability across IRT parameters are mostly artifacts of calibration noise rather than text signal.
Proceedings of the 2021 conference on empirical methods in natural language processing , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
A shallow neural network mapping item content features to 6-dimensional embeddings, fit jointly with latent abilities via Monte Carlo EM, achieves competitive held-out calibration on two Duolingo English Test task types.
citing papers explorer
-
From Text to Parameters: Predicting Item Parameters from Embedding Regularization with Reliability and Design Ceilings
Text embeddings recover 57-63% of the reliable variance in exam-item difficulty, and apparent differences in predictability across IRT parameters are mostly artifacts of calibration noise rather than text signal.
-
Learning Item Embeddings and Hyperparameters for IRT Calibration via Monte Carlo EM
A shallow neural network mapping item content features to 6-dimensional embeddings, fit jointly with latent abilities via Monte Carlo EM, achieves competitive held-out calibration on two Duolingo English Test task types.