Abstract
When cooking, it can sometimes be desirable to substitute ingredients for purposes such as avoiding allergens, replacing a missing ingredient, or exploring new flavors. More generally, the problem of substituting entities used in procedural instructions is challenging as it requires an understanding of how entities and actions in the instructions interact to produce the final result. To support the task of automatically identifying viable substitutions, we introduce a methodology to (1) parse instructions, using NLP tools and domain-specific ontologies, to generate flow graph representations, (2) train a novel embedding model which captures flow and interaction of entities in each step of the instructions, and (3) utilize the embeddings to identify plausible substitutions. Our embedding strategy aggregates nodes and dynamically computes intermediate results within the flow graphs, which requires learning embeddings for fewer nodes than typical graph embedding models. Our rule-based flow graph generation method shows comparable performance to machine learning-based work, while our embedding model outperforms baselines on a link-prediction task for ingredients in recipes.
S. S. Shirai—Part of this work was done while the author was an intern at Robert Bosch LLC.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We refer to Sect. 1 in our supplemental material for further details on this process.
- 2.
We refer to Sect. 2 in our supplemental material for details on the preprocessing.
- 3.
Further details are discussed in Sect. 2 of our supplemental material.
- 4.
Jicama and rutabaga are often cited as healthy potato substitutes.
- 5.
We refer to Sect. 3 in our supplemental material for details on the example recipes.
References
Agarwal, S., Atreja, S., Agarwal, V.: Extracting procedural knowledge from technical documents. ArXiv abs/2010.10156 (2020)
Bordes, A., Usunier, N., García-Durán, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: NIPS (2013)
Dooley, D.M., et al.: Foodon: a harmonized food ontology to increase global food traceability, quality control and data integration. NPJ Science of Food 2 (2018)
Dufour-Lussier, V., Ber, F.L., Lieber, J., Meilender, T., Nauer, E.: Semi-automatic annotation process for procedural texts: an application on cooking recipes. ArXiv abs/1209.5663 (2012)
Gaillard, E., Lieber, J., Nauer, E.: Adaptation of taaable to the ccc’2017 mixology and salad challenges, adaptation of the cocktail names. In: ICCBR (Workshops), pp. 253–268 (2017)
Halioui, A., Valtchev, P., Diallo, A.B.: Ontology-based workflow extraction from texts using word sense disambiguation. bioRxiv (2016)
Hamada, R., Ide, I., Sakai, S., Tanaka, H.: Structural analysis of cooking preparation steps in Japanese. In: IRAL 2000 (2000)
Hamilton, W.L., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: NIPS (2017)
Honnibal, M., Montani, I., Van Landeghem, S., Boyd, A.: spacy: Industrial-strength natural language processing in python (2020)
Kiddon, C., Ponnuraj, G.T., Zettlemoyer, L., Choi, Y.: Mise en place: unsupervised interpretation of instructional recipes. In: EMNLP (2015)
Kipf, T., Welling, M.: Semi-supervised classification with graph convolutional networks. ICLR (2017)
Kulkarni, C., Xu, W., Ritter, A., Machiraju, R.: An annotated corpus for machine reading of instructions in wet lab protocols. In: NAACL (2018)
Maeta, H., Sasada, T., Mori, S.: A framework for procedural text understanding. In: IWPT (2015)
Majumder, B.P., Li, S., Ni, J., McAuley, J.: Generating personalized recipes from historical user preferences. In: EMNLP-IJCNLP, pp. 5976–5982. Association for Computational Linguistics, Hong Kong, China, November 2019
Mori, S., Maeta, H., Yamakata, Y., Sasada, T.: Flow graph corpus from recipe texts. In: LREC (2014)
Mysore, S., et al.: Automatically extracting action graphs from materials science synthesis procedures. CoRR abs/1711.06872 (2017). http://arxiv.org/abs/1711.06872
Nathani, D., Chauhan, J., Sharma, C., Kaul, M.: Learning attention-based embeddings for relation prediction in knowledge graphs. In: ACL (2019)
Nguyen, D.Q., Nguyen, T.D., Nguyen, D.Q., Phung, D.Q.: A novel embedding model for knowledge base completion based on convolutional neural network. In: NAACL (2018)
Schumacher, P., Minor, M., Walter, K., Bergmann, R.: Extraction of procedural knowledge from the web: a comparison of two workflow extraction approaches. WWW (2012)
Shirai, S.S., Seneviratne, O., Gordon, M.E., Chen, C.H., McGuinness, D.L.: Identifying ingredient substitutions using a knowledge graph of food. Front. Artif. Intell. 3, 111 (2021)
Skjold, K., Øynes, M., Bach, K., Aamodt, A.: Intellimeal-enhancing creativity by reusing domain knowledge in the adaptation process. In: ICCBR (Workshops), pp. 277–284 (2017)
Sun, Z., Deng, Z., Nie, J.Y., Tang, J.: Rotate: Knowledge graph embedding by relational rotation in complex space. ICLR (2019)
Trouillon, T., Welbl, J., Riedel, S., Gaussier, É., Bouchard, G.: Complex embeddings for simple link prediction. In: ICML (2016)
Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Lio’, P., Bengio, Y.: Graph attention networks. ICLR (2018)
Wang, L., Li, Q., Li, N., Dong, G., Yang, Y.: Substructure similarity measurement in Chinese recipes. In: WWW (2008)
Wang, Q., Mao, Z., Wang, B., Guo, L.: Knowledge graph embedding: a survey of approaches and applications. IEEE Trans. Knowl. Data Eng. 29, 2724–2743 (2017)
Yamakata, Y., Imahori, S., Maeta, H., Mori, S.: A method for extracting major workflow composed of ingredients, tools, and actions from cooking procedural text. In: 2016 IEEE International Conference on Multimedia Expo Workshops (ICMEW), pp. 1–6 (2016)
Yamakata, Y., Mori, S., Carroll, J.: English recipe flow graph corpus. In: LREC (2020)
Yang, B., tau Yih, W., He, X., Gao, J., Deng, L.: Embedding entities and relations for learning and inference in knowledge bases. CoRR abs/1412.6575 (2015)
Zhang, Z., Webster, P., Uren, V.S., Varga, A., Ciravegna, F.: Automatically extracting procedural knowledge from instructional texts using natural language processing. In: LREC (2012)
Zhu, G., Iglesias, C.A.: Computing semantic similarity of concepts in knowledge graphs. IEEE TKDE 29(1), 72–85 (2017)
Acknowledgements
We would like to express our thanks to the colleagues of Bosch’s RTC-NA, the members of RPI’s Tetherless World Constellation, and CMU’s Naoki Otani for their feedback and reviews of this manuscript.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Shirai, S.S., Kim, H. (2022). EaT-PIM: Substituting Entities in Procedural Instructions Using Flow Graphs and Embeddings. In: Sattler, U., et al. The Semantic Web – ISWC 2022. ISWC 2022. Lecture Notes in Computer Science, vol 13489. Springer, Cham. https://doi.org/10.1007/978-3-031-19433-7_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-19433-7_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19432-0
Online ISBN: 978-3-031-19433-7
eBook Packages: Computer ScienceComputer Science (R0)