Transduce:学习用于字符串变换的转导文法
Transduce: learning transduction grammars for string transformation
AI总结:
针对示例驱动的字符串变换程序合成问题,本文提出 Transduce 算法,通过构建并泛化抽象转导文法,在无归纳偏置条件下仅凭一两个正例即可高效学习位置变换,成功率超过现有方法。
摘要:
从输入-输出示例中综合字符串变换程序会用到多种技术,这些技术都基于一种归纳偏置,即包含一组受限的、可供组合的基本算子。本文提出一种名为 Transduce 的新算法,其基础是构建抽象转导文法并对其进行泛化。我们通过实验证明,Transduce 能够在没有归纳偏置的情况下,仅从一个或两个正例中高效学习位置变换,并取得高于当前最先进水平的成功率。
英文摘要:
The synthesis of string transformation programs from input-output examples utilizes various techniques, all based on an inductive bias that comprises a restricted set of basic operators to be combined. A new algorithm, Transduce, is proposed, which is founded on the construction of abstract transduction grammars and their generalization. We experimentally demonstrate that Transduce can learn positional transformations efficiently from one or two positive examples without inductive bias, achieving a success rate higher than the current state of the art.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。