Yanbo Fang


pdf bib
Assessing Combinational Generalization of Language Models in Biased Scenarios
Yanbo Fang | Zuohui Fu | Xin Dong | Yongfeng Zhang | Gerard de Melo
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

In light of the prominence of Pre-trained Language Models (PLMs) across numerous downstream tasks, shedding light on what they learn is an important endeavor. Whereas previous work focuses on assessing in-domain knowledge, we evaluate the generalization ability in biased scenarios through component combinations where it could be easy for the PLMs to learn shortcuts from the training corpus. This would lead to poor performance on the testing corpus, which is combinationally reconstructed from the training components. The results show that PLMs are able to overcome such distribution shifts for specific tasks and with sufficient data. We further find that overfitting can lead the models to depend more on biases for prediction, thus hurting the combinational generalization ability of PLMs.