The Interactive Cookbook

互动食谱

• 批准号: 461220770
• 负责人: Professor Dr. Alexander Koller
• 金额: --
• 依托单位: Lehrstuhl für Computerlinguistik (Prof Koller)
• 依托单位国家: 德国
• 项目类别: Research Grants
• 资助国家: 德国
• 项目状态: 未结题
• 来源: https://gepris.dfg.de/gepris/projekt/461220770?language=en
• 关键词: Interactive; Cookbook

The goal of this project is to develop an "Interactive Cookbook": a spoken dialogue system that guides users through the process of cooking a dish. The system will analyze individual recipe texts for a given dish offline and aggregate them into a symbolic recipe graph, which captures alternative ways in which the recipe can be explained and carried out. At dialogue time, a natural language understanding (NLU) component will process user requests regarding the dish, and a natural language generation (NLG) component will generate step-by-step instructions in English or German based on the recipe graph. The dialogue system will adapt the level of detail at which it presents the recipe to the user's needs.In developing such an Interactive Cookbook, we will face a number of research challenges. First, cooking recipes are a rather specific type of text, and NLU methods trained on main- stream corpora will have to be adapted to the recipe domain. We will also consolidate different recipes for the same dish into a single representation, so we can switch to different levels of detail as required for the user.Second, we will have to refine neural word embeddings to capture domain-specific meaning distinctions: “salt” and “sugar” are distributionally very similar, but confusing one for the other in a recipe will drastically change the dish.Finally, we will have to move beyond current methods in NLG: grammar-based methods run into coverage problems when explaining arbitrary recipes, and neural methods such as those in recent approaches to abstractive summarization struggle to produce language which conveys a given meaning. One focus of the project will therefore be to generate instructions which are semantically true to the underlying recipes, by conditioning a neural NLG system on symbolic recipe graphs.

该项目的目的是开发“互动食谱”：一种口语对话系统，可指导用户烹饪菜的过程。该系统将分析离线给定的菜肴的单个食谱文本，并将其汇总成符号食谱图，该图形捕获了可以解释和执行配方的替代方法。在对话时，自然语言理解（NLU）组件将处理用户有关该菜肴的请求，而自然语言生成（NLG）组件将根据食谱图生成英语或德语的逐步指令。对话系统将调整其为用户需求提供食谱的细节水平。在开发这种交互式食谱时，我们将面临许多研究挑战。首先，烹饪食谱是一种相当特定的文本类型，在主流语料库中训练的NLU方法必须适应食谱域。我们还将将同一道菜的不同食谱整合到单一的表示中，因此我们可以根据用户的要求切换到不同的细节。在解释任意食谱时会遇到覆盖问题，以及在最近的抽象摘要方法中的神经方法（例如，诸如抽象摘要方法中的方法都难以产生传达给定含义的语言。因此，该项目的一个重点是通过在符号食谱图上调节神经元NLG系统在语义上真实的指令。