提出三元组线性化方法，改进AMR解析中图结构的序列化表示。
Reassessing Graph Linearization for Sequence-to-sequence AMR Parsing: On the Advantages and Limitations of Triple-Based Encoding
- 用三元组替代树结构编码，减少节点重入带来的关系类型翻倍问题。
- 实验显示三元组法在深层图上节点距离更近，但整体表现仍落后于Penman编码。
- 适合关注图结构建模与序列化优化的研究者参考。
序列到序列模型被广泛用于训练抽象语义表示（AMR）解析器。为训练此类模型，需将AMR图线性化为单行文本格式。尽管通常使用Penman编码，但其存在局限：（1）对于深层图，紧密相关的节点在文本中可能相距甚远；（2）基于树的编码要求引入反向角色处理节点重入，使需预测的关系类型数量翻倍。为此，我们提出一种三元组基线性化方法，并与Penman线性化进行效率对比。虽然三元组在表达图结构上具有优势，但实验结果表明，其编码方式在竞争中仍不及Penman对嵌套结构的简洁且明确表达。
原文摘要 · Abstract (English)
Sequence-to-sequence models are widely used to train Abstract Meaning Representation (Banarescu et al., 2013, AMR) parsers. To train such models, AMR graphs have to be linearized into a one-line text format. While Penman encoding is typically used for this purpose, we argue that it has limitations: (1) for deep graphs, some closely related nodes are located far apart in the linearized text (2) Penman's tree-based encoding necessitates inverse roles to handle node re-entrancy, doubling the number of relation types to predict. To address these issues, we propose a triple-based linearization method and compare its efficiency with Penman linearization. Although triples are well suited to represent a graph, our results suggest room for improvement in triple encoding to better compete with Penman's concise and explicit representation of a nested graph structure.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。