重新排列熟悉的事物：在递归网络中测试组合泛化
Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networks
摘要：
系统组合性是将有意义的单位与规则和可预测的结果重新组合的能力，它被视为人类语言概括能力的关键。最近的工作研究了现代seq2seq模型中的系统组合性，在接地环境中使用泛化到新的导航指令作为探测工具，要求模型快速引导新单词的含义。我们在这里将这个框架扩展到模型只需要在新的上下文中重新组合训练有素的功能词（如“around”和“right”）的设置。我们的研究结果证实并加强了早期的研究结果：seq2seq模型可以令人印象深刻地善于推广到以前看到的输入的新组合，但只有当它们接受了关于要推广的特定模式的广泛训练时（例如，从“右周围X”到“右周围跳跃”的许多示例中概括），而当概括需要合成规则的新颖应用时失败（例如，从“右”和“左右”的含义推断“左右”的含义）。
英文摘要：
Systematic compositionality is the ability to recombine meaningful units with regular and predictable outcomes, and it's seen as key to humans' capacity for generalization in language. Recent work has studied systematic compositionality in modern seq2seq models using generalization to novel navigation instructions in a grounded environment as a probing tool, requiring models to quickly bootstrap the meaning of new words. We extend this framework here to settings where the model needs only to recombine well-trained functional words (such as "around" and "right") in novel contexts. Our findings confirm and strengthen the earlier ones: seq2seq models can be impressively good at generalizing to novel combinations of previously-seen input, but only when they receive extensive training on the specific pattern to be generalized (e.g., generalizing from many examples of "X around right" to "jump around right"), while failing when generalization requires novel application of compositional rules (e.g., inferring the meaning of "around right" from those of "right" and "around").
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。
