arXiv cs.AI· Anuj Kumar, Shintaro Ozaki, Yamuna Prasad, Katsuhiko Hayashi, Hidetaka Kamigaito, Taro Watanabe·· 6 小时前AI 评分22
AMR 解析器输出有多可靠？AMR 解析的不确定性估计研究
How Reliable are AMR Parser Outputs? Uncertainty Estimation for AMR Parsing
AI 导读
AMR 解析器性能大幅提升，但其输出何时可信此前缺乏研究。该工作首次在黑盒设置下利用 top-k beam-search 候选做 AMR 解析的不确定性估计，通过候选间成对相似度计算不确定性，并用 Prediction Rejection Ratio 评估。实验分析了性能与不确定性的关系、beam 候选分布的可靠性及评测指标的影响，表明不确定性估计可作为评估 AMR 解析器的补充维度。
正文 · 原文
Abstract:Recent advances have significantly improved the performance of Abstract Meaning Representation (AMR) parsers, yet determining when their outputs can be trusted remains largely unexplored. This work presents the first study of uncertainty estimation for AMR parsers in a black-box setting using top-k beam-search candidates. Uncertainty is estimated from pairwise candidate similarities and evaluated using the Prediction Rejection Ratio. This work characterises the relationship between parsing performance and uncertainty, evaluates the reliability of beam candidate distributions, analyses the effect of evaluation metrics on uncertainty assessment, and identifies parsers that provide the strongest balance between performance and reliability. Experimental results show the value of uncertainty estimation as a complementary dimension for evaluating AMR parsers.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.13236 [cs.CL] |
| (or arXiv:2610.13236v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13236 arXiv-issued DOI via DataCite |
Submission history
From: Anuj Kumar [view email]
[v1]
Fri, 9 Oct 2026 08:53:02 UTC (217 KB)
[v2]
Sun, 25 Oct 2026 04:47:09 UTC (217 KB)
来源：arXiv cs.AI · arxiv.org