%0 Conference Proceedings %T Improving Compositional Generalization in Classification Tasks via Structure Annotations %A Kim, Juyong %A Ravikumar, Pradeep %A Ainslie, Joshua %A Ontanon, Santiago %Y Zong, Chengqing %Y Xia, Fei %Y Li, Wenjie %Y Navigli, Roberto %S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers) %D 2021 %8 August %I Association for Computational Linguistics %C Online %F kim-etal-2021-improving %X Compositional generalization is the ability to generalize systematically to a new data distribution by combining known components. Although humans seem to have a great ability to generalize compositionally, state-of-the-art neural models struggle to do so. In this work, we study compositional generalization in classification tasks and present two main contributions. First, we study ways to convert a natural language sequence-to-sequence dataset to a classification dataset that also requires compositional generalization. Second, we show that providing structural hints (specifically, providing parse trees and entity links as attention masks for a Transformer model) helps compositional generalization. %R 10.18653/v1/2021.acl-short.81 %U https://aclanthology.org/2021.acl-short.81 %U https://doi.org/10.18653/v1/2021.acl-short.81 %P 637-645