Feature Extraction and Summarization of Recipes Using Flow Graph
These days, there are more than a million recipes on the Web. When you search for a recipe with one query such as “nikujaga,” the name of a typical Japanese food, you can find thousands of “nikujaga” recipes as the result. Even if you focus on only the top ten results, it is still difficult to find out the characteristic feature of each recipe because a cooking is a work-flow including parallel procedures. According to our survey, people place the most importance on the differences of cooking procedures when they compare the recipes. However, such differences are difficult to be extracted just by comparing the recipe texts as existing methods. Therefore, our system extracts (i) a general way to cook as a summary of cooking procedures and (ii) the characteristic features of each recipe by analyzing the work-flows of the top ten results. In the experiments, our method succeeded in extracting 54% of manually extracted features while the previous research addressed 37% of them.
KeywordsEdit Distance Flow Graph Name Entity Recognition Edit Operation Name Entity
Unable to display preview. Download preview PDF.
- 1.Demaine, E.D., Mozes, S., Rossman, B., Weimann, O.: An optimal decomposition algorithm for tree edit distance. ACM Trans. on Algorithms 6, Article No. 2 (2009)Google Scholar
- 2.Do, H.-H., Rahm, E.: COMA – a system for flexible combination of schema matching approaches. In: Proc. of the 28th International Conference on Very Large Data Bases, pp. 610–621 (2002)Google Scholar
- 3.Hamada, R., Ide, I., Sakai, S., Tanaka, H.: Structural analysis of cooking preparation steps. IEICE Trans. J85-D-II, 79–89 (2002) (in Japanese)Google Scholar
- 4.Karikome, S., Fujii, A.: Improving structural analysis of cooking recipe text. IEICE Technical Report 112(75), DE2012-8, 43–48 (2012) (in Japanese)Google Scholar
- 5.Mori, S., Sasada, T., Yamakata, Y., Yoshino, K.: A machine learning approach to recipe text processing. In: Cooking with Computers Workshop, pp. 1–6 (2012)Google Scholar
- 7.Sang, E.F.T.K., Meulder, F.D.: Introduction to the CoNLL-2003 shared task: language-independent named entity recognition. In: Proc. of CoNLL 2003, pp. 142–147 (2003)Google Scholar
- 10.Tsukuda, K., Nakamura, S., Yamamoto, T., Tanaka, K.: Recommendation of addition and deletion ingredients based on the recipe structure and its stability for exploration of recipes. IEICE Trans. J94-A, 476–487 (2011) (in Japanese)Google Scholar
- 11.Yamakata, Y., Kakusho, K., Minoh, M.: A method of recipe to cooking video mapping for automated cooking content construction. IEICE Trans. Inf. & Syst. J90-D, 2817–2829 (2007) (in Japanese)Google Scholar
- 12.Yoshino, K., Mori, S., Kawahara, T.: Predicate argument structure analysis using partially annotated corpora. In: Proc. of the Sixth International Joint Conference on Natural Language Processing (to appear)Google Scholar
- 14.COOKPAD (May 29, 2013), http://cookpad.com/ (in Japanese)