AI 中文总结
通过将符号后端改为CCG有向类型，系统在SLOG的方向性类别上显著超越AM-Parser，而AM-Parser在递归深度类别上更优，表明方向性表示将瓶颈从符号层转移到神经层。
AI 中文摘要
几个SLOG测试类别明确涉及方向性区分（修饰语位置移动、论元提取位置），但之前的SOTA模型AM-Parser使用的AM代数操作不编码方向。我们围绕CCG有向类型（确定性CKY + 单线性解码器，30K可学习参数）重新设计了符号后端。在相同的BERT-base编码器下，系统达到75.9±6.4%的LF精确匹配，超过了AM-Parser（70.8±4.3%）。根据SLOG自身的类别分组，增益高度方向性：CCG系统在所有5个位置移动类别上优于AM-Parser（+29.9pp），而AM-Parser在所有6个递归深度类别上更优。将编码器替换为DeBERTa-v3-large后，达到90.7±4.9%，最大的编码器增益出现在递归深度类别中，与方向性增益互补。方向性表示将瓶颈从符号层（AM-Parser的0%类别上限）转移到神经层，而神经层随着编码器升级而改善。
英文摘要
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.
CommentsWe have identified an evaluation-metric mismatch in this preprint (reported LF exact match was computed against a final-state proxy, not against predicted LF edges). We withdraw the claims in this version. A corrected approach with true LF evaluation is in preparation
