这篇论文用CCG方向类型替换AM-Parser的代数，在结构泛化基准上提升了5个百分点的LF精确匹配，尤其在位置偏移任务上提升近30个百分点。
论文提出用CCG方向类型替换AM-Parser的无方向AM代数，使用确定性CKY算法和单线性解码器，仅30K可学习参数。在BERT-base编码器下，LF exact match达75.9±6.4%，超过AM-Parser的70.8±4.3%。SLOG测试中，CCG在5个位置偏移类别上高出29.9个百分点，但AM-Parser在6个递归深度类别上更优。换用DeBERTa-v3-large后成绩升至90.7±4.9%，且编码器升级主要提升递归深度类别。实验证明方向性表示将瓶颈从符号层转向神经层。
On the Role of Directionality in Structural Generalization
Several SLOG test categories explicitly involve directional distinctions (modifier position shifts, argument extraction positions), yet AM-Parser, the previous SOTA, uses an AM algebra whose operations do not encode direction. We redesign the symbolic backend around CCG directed types (deterministic CKY + single linear decoder, 30K learnable parameters). Under the same BERT-base encoder, the system achieves 75.9$\pm$6.4% LF exact match, surpassing AM-Parser (70.8$\pm$4.3%). Per SLOG's own category groupings, gains are highly directional: the CCG system outperforms AM-Parser on all 5 position-shift categories (+29.9pp), while AM-Parser outperforms on all 6 recursive-depth categories. Replacing the encoder with DeBERTa-v3-large yields 90.7$\pm$4.9%, with the largest encoder gains in recursive-depth categories, complementary to directionality's gains. Directional representations shift the bottleneck from the symbolic layer (AM-Parser's 0% category ceiling) to the neural layer, which improves with encoder upgrades.