Hierarchical Poset Decoding for Compositional Generalization in Language
This addresses compositional generalization in natural language processing, which is crucial for robust AI systems, though it appears incremental as it builds on existing encoder-decoder architectures.
The paper tackles the problem of poor compositional generalization in language understanding by formalizing it as structured prediction with partially ordered sets (posets), proposing a hierarchical poset decoding paradigm that outperforms current decoders on the Compositional Freebase Questions dataset.
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.