KitchenScale：学习从食谱上下文预测食材用量
KitchenScale: Learning to predict ingredient quantities from recipe contexts
AI总结：
本文提出 KitchenScale 微调 PLM，通过计量类型分类、单位分类、用量回归及 DExp 方法，从食谱上下文预测食材数值与单位，并验证其泛化能力。
摘要：
从提升美味程度和促进健康的角度来看，确定食材的适当用量是烹饪实践中的重要环节。我们提出 KitchenScale，这是一种经过微调的预训练语言模型（PLM），能够根据给定的食谱上下文预测目标食材的用量和计量单位。为了有效训练 KitchenScale 模型，我们将食材用量预测任务形式化为三个子任务，分别是食材计量类型分类、单位分类和用量回归任务。此外，我们利用从食谱文本到 PLM 的烹饪知识迁移学习，并采用离散潜在指数（Discrete Latent Exponent，DExp）方法来应对食谱语料库中数值尺度的高方差问题。在我们新构建的数据集上进行的实验以及推荐示例表明，KitchenScale 能够理解各种食谱上下文，并在预测食材用量方面具有泛化能力。我们为 KitchenScale 实现了一个 Web 应用程序，以展示其推荐以数字（例如 2）加单位（例如盎司）表示的食材用量的功能。
英文摘要：
Determining proper quantities for ingredients is an essential part of cooking practice from the perspective of enriching tastiness and promoting healthiness. We introduce KitchenScale, a fine-tuned Pre-trained Language Model (PLM) that predicts a target ingredient's quantity and measurement unit given its recipe context. To effectively train our KitchenScale model, we formulate an ingredient quantity prediction task that consists of three sub-tasks which are ingredient measurement type classification, unit classification, and quantity regression task. Furthermore, we utilized transfer learning of cooking knowledge from recipe texts to PLMs. We adopted the Discrete Latent Exponent (DExp) method to cope with high variance of numerical scales in recipe corpora. Experiments with our newly constructed dataset and recommendation examples demonstrate KitchenScale's understanding of various recipe contexts and generalizability in predicting ingredient quantities. We implemented a web application for KitchenScale to demonstrate its functionality in recommending ingredient quantities expressed in numerals (e.g., 2) with units (e.g., ounce).
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。
