Cooking Recipe Search by Pairs of Ingredient and Action —Word Sequence v.s. Flow-graph Representation—
Cooking Recipe Search by Pairs of Ingredient and Action —Word Sequence v.s. Flow-graph Representation—
复制标题
DOI：
10.1527/tjsai.wii-f
复制
发表时间：
2017-01
影响因子：
--
通讯作者：
Yoko Yamakata;Hirokuni Maeta;Takuya Kadowaki;Tetsuro Sasada;S. Imahori;Shinsuke Mori
中科院分区：
文献类型：
--
作者：
Yoko Yamakata;Hirokuni Maeta;Takuya Kadowaki;Tetsuro Sasada;S. Imahori;Shinsuke Mori
本文提出了一种通过“a tomato is fried”这样的程序来搜索烹饪食谱的方法。虽然大多数烹饪食谱搜索方法都将食谱文本视为单词袋（BoW），但它错误地发现了这样的食谱：“将洋葱油炸，并与西红柿立方体（其中西红柿没有加热）一起食用。”我们的方法使用依赖解析技术提前自动将过程文本转换为流程图。在流程图中，通过跟踪从与成分对应的节点到与最后一个动作对应的根节点的路径，可以很容易地提取将对成分执行的操作序列。我们将该方法与任务适应的BoW模型作为基线进行比较，结果表明该方法的准确率为68.8%，而基线方法的准确率为61.5%。
This paper proposes a method for searching cooking recipes by a procedure such as “a tomato is fried.” Although most of methods for cooking recipe search treat recipe text as Bag-of-Words (BoW), it misdetects such a recipe that “fry an onion deeply and serve it with a tomato cube (in which the tomato is not heated).” Our method converts a procedural text to a flow-graph automatically in advance using a dependency parsing technique. In the flow-graph, action sequence that will be performed to an ingredient is easily extracted by tracing the path from the node corresponding to the ingredient to the root node corresponding to the last action. We evaluate our method comparing with a task adapted BoW model as a baseline and the proposed method achieved a precision of 68.8% while the baseline method achieved it of 61.5%.