Unsupervised Learning of Graph from Recipes
This work addresses the challenge of procedural text understanding for applications in cooking and related domains, presenting an incremental improvement over existing methods.
The paper tackles the problem of interpreting natural language instructions in cooking recipes by proposing an unsupervised model that generates a graph to represent the sequence of actions, achieving results comparable to state-of-the-art methods through evaluation on annotated datasets and text reconstruction.
Cooking recipes are one of the most readily available kinds of procedural text. They consist of natural language instructions that can be challenging to interpret. In this paper, we propose a model to identify relevant information from recipes and generate a graph to represent the sequence of actions in the recipe. In contrast with other approaches, we use an unsupervised approach. We iteratively learn the graph structure and the parameters of a $\mathsf{GNN}$ encoding the texts (text-to-graph) one sequence at a time while providing the supervision by decoding the graph into text (graph-to-text) and comparing the generated text to the input. We evaluate the approach by comparing the identified entities with annotated datasets, comparing the difference between the input and output texts, and comparing our generated graphs with those generated by state of the art methods.