通过批评进行辅助食谱编辑
Assistive Recipe Editing through Critiquing
摘要：
最近，人们对自动生成满足某种形式的饮食限制的烹饪食谱越来越感兴趣，这部分归功于在线食谱数据的可用性。先前的研究已经使用了预先训练的语言模型，或者依赖于小的配对食谱数据（例如，与满足饮食约束的类似食谱配对的食谱）。然而，预先训练的语言模型生成不一致或不连贯的配方，并且配对的数据集在规模上不可用。我们用RecipeCrit解决了这些缺陷，RecipeCrit是一种分层去噪自动编码器，可以根据配料级别的评论编辑食谱。该模型被训练用于配方完成，以学习配方内的语义关系。我们工作的主要创新是我们的无监督批评模块，允许用户通过与预测的成分交互来编辑食谱;系统迭代重写食谱以满足用户的反馈。在Recipe 1 M食谱数据集上的实验表明，与强大的语言建模基线相比，我们的模型可以更有效地编辑食谱，创建满足用户约束的食谱，并且根据人类判断，这些食谱更加正确，偶然，连贯和相关。
英文摘要：
There has recently been growing interest in the automatic generation of cooking recipes that satisfy some form of dietary restrictions, thanks in part to the availability of online recipe data. Prior studies have used pre-trained language models, or relied on small paired recipe data (e.g., a recipe paired with a similar one that satisfies a dietary constraint). However, pre-trained language models generate inconsistent or incoherent recipes, and paired datasets are not available at scale. We address these deficiencies with RecipeCrit, a hierarchical denoising auto-encoder that edits recipes given ingredient-level critiques. The model is trained for recipe completion to learn semantic relationships within recipes. Our work's main innovation is our unsupervised critiquing module that allows users to edit recipes by interacting with the predicted ingredients; the system iteratively rewrites recipes to satisfy users' feedback. Experiments on the Recipe1M recipe dataset show that our model can more effectively edit recipes compared to strong language-modeling baselines, creating recipes that satisfy user constraints and are more correct, serendipitous, coherent, and relevant as measured by human judges.
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。
