让自然语言转信号时序逻辑更准，保留语义歧义的多种可能
Structural-Ambiguity-Aware Translation from Natural Language to Signal Temporal Logic
- 用组合范畴语法保留自然语言的多种语法解析
- 生成多个候选时序逻辑公式并赋予可信度评分
- 适合非专家用户描述复杂安全任务，避免误译
信号时序逻辑（STL）广泛用于定义网络物理系统的时序与安全关键任务，但非专家难以直接编写STL公式。自然语言虽易用，但其固有的结构歧义导致一对一转换不可靠。本文提出一种‘歧义保留’方法，将自然语言任务描述转为STL候选公式。核心思想是在解析阶段不强制选择单一解释，而是保留多种合理语法分析。基于组合范畴语法（CCG），构建三阶段流水线：歧义保留的n-best解析、面向STL的模板化语义组合、基于得分聚合的标准化。最终输出去重后的STL候选集及其置信度，显式表示模糊指令的多重形式解释。相比现有单解法，本方法能有效保留依存和作用域歧义。在典型任务描述上的案例研究显示，对真正模糊输入生成多个候选公式，而对无歧义或等价的推导则合并为单一STL公式。
原文摘要 · Abstract (English)
Signal Temporal Logic (STL) is widely used to specify timed and safety-critical tasks for cyber-physical systems, but writing STL formulas directly is difficult for non-expert users. Natural language (NL) provides a convenient interface, yet its inherent structural ambiguity makes one-to-one translation into STL unreliable. In this paper, we propose an \textit{ambiguity-preserving} method for translating NL task descriptions into STL candidate formulas. The key idea is to retain multiple plausible syntactic analyses instead of forcing a single interpretation at the parsing stage. To this end, we develop a three-stage pipeline based on Combinatory Categorial Grammar (CCG): ambiguity-preserving $n$-best parsing, STL-oriented template-based semantic composition, and canonicalization with score aggregation. The proposed method outputs a deduplicated set of STL candidates with plausibility scores, thereby explicitly representing multiple possible formal interpretations of an ambiguous instruction. In contrast to existing one-best NL-to-logic translation methods, the proposed approach is designed to preserve attachment and scope ambiguity. Case studies on representative task descriptions demonstrate that the method generates multiple STL candidates for genuinely ambiguous inputs while collapsing unambiguous or canonically equivalent derivations to a single STL formula.
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。