We formalize human language understanding as a structured prediction task where the output is a partially ordered set (poset). Current encoder-decoder architectures do not take the poset structure of semantics into account properly, thus suffering from poor compositional generalization ability. In this paper, we propose a novel hierarchical poset decoding paradigm for compositional generalization in language. Intuitively: (1) the proposed paradigm enforces partial permutation invariance in semantics, thus avoiding overfitting to bias ordering information; (2) the hierarchical mechanism allows to capture high-level structures of posets. We evaluate our proposed decoder on Compositional Freebase Questions (CFQ), a large and realistic natural language question answering dataset that is specifically designed to measure compositional generalization. Results show that it outperforms current decoders.
@article{arxiv.2010.07792,
title = {Hierarchical Poset Decoding for Compositional Generalization in Language},
author = {Yinuo Guo and Zeqi Lin and Jian-Guang Lou and Dongmei Zhang},
journal= {arXiv preprint arXiv:2010.07792},
year = {2020}
}