概述
Restoring missing text in a known language differs from establishing the meaning of an unknown script.
深入探讨
Ithaca predicts missing text and geographic and chronological attribution for ancient Greek inscriptions. It uses textual context to produce candidate restorations, which scholars assess against the inscription and historical evidence. A separate 2019 neural decipherment paper evaluates Ugaritic with Hebrew and Linear B with Greek; these are separate language-pair experiments, not translation from Ugaritic into Linear B. Its input includes a non-parallel corpus in a known related language, so it does not require aligned bilingual sentences. A character-based sequence-to-sequence model learns correspondences between cognates. Monotonic alignment regularization encourages order-preserving character mappings, while minimum-cost flow constrains the global assignment of words across vocabularies. These assumptions and benchmark results do not prove that an unrelated, insufficiently documented script has been deciphered. Scholars must test proposed readings against independent contextual and linguistic evidence.
现实世界的实施
Use Ithaca to rank candidate restorations of ancient Greek inscriptions.
Compare proposed dates and locations with historical evidence.
Study character and word correspondences using a known related language.
Preserve alternative readings for expert assessment.
人工智能在古代语言破译中的未来
AI-assisted decipherment is a research aid. Report uncertainty and avoid claiming a script has been decoded without scholarly validation.
付诸实践
为什么这很重要
- 构建选择. 应用级设计决定了人工智能是否能改善实际结果。
- 团队与工作流程. 良好的工作流程集成可以创造用户值得信赖的生产力收益。
- 风险与安全. 范围明确的用例可以减少变更疲劳和实施风险。
留意
- 将损坏的流程自动化可能会加剧现有问题。
- 团队可能会过度自动化并消除所需的人工判断。
- 如果不持续评估输出，质量可能会出现偏差。
后续步骤
- 绘制当前工作流程并确定摩擦最大的步骤。
- 在完全自动化之前定义人工检查点。
- 对用户进行提示、升级路径和质量标准方面的培训。
- 跟踪任务级结果以确认持续价值。
不断探索
常见问题
What is AI in Ancient Language Decipherment?
AI can propose restorations and linguistic alignments for scholarly analysis. Restoring missing text in a known language differs from establishing the meaning of an unknown script.
DeepMind 的伊萨卡模型对古希腊铭文有何作用？
伊萨卡接受了数以万计的希腊铭文的训练，以修复受损的段落并预测它们的书写时间和地点，从而为历史学家提供帮助。
当古代文本破损或磨损时，序列模型有何帮助？
该模型在完整文本上进行训练，通过预测可能的字符（类似于自动完成）来填补掩盖的空白，并提供排名的候选者。
What character-alignment assumption does the 2019 neural decipherment paper encourage for cognates?
The paper regularizes cognate alignment toward monotonic rewriting as a linguistic modeling assumption. It is not a universal law for all language change.
什么是破译上下文中的跨语言对齐？
通过将未知语言映射到假设的亲属上，并对是否出现真实单词进行评分，研究人员可以测试关系，就像乌加里特语和希伯来语所做的那样。
这些模型通常如何在内部表示脚本？
脚本被视为文本序列；该模型了解哪些符号倾向于遵循哪些符号，从而实现恢复和模式发现。