Unsupervised Learning of Graph from Recipes
Not on the map. Why?
Abstract (arXiv)
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 mathsfGNN 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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 59 references that are in the map. First posted on arXiv 22 Jan 2024.
Builds on
33 of 59 references.
References · 33
- 2017Attention Is All You Needcited by 60,361
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
- 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
- 2016Variational Graph Auto-Encoderscited by 1,382
- 2018Hierarchical Neural Story Generationcited by 1,193
- 2014Show and Tell: A Neural Image Caption Generatorcited by 879
- 2017Convolutional Sequence to Sequence Learningcited by 552
- 2018MolGAN: An implicit generative model for small molecular graphscited by 393
- 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 305
- 2019Efficient Graph Generation with Graph Recurrent Attention Networkscited by 234
21 more
- 2016Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioningcited by 232
- 2019Learning Discrete Structures for Graph Neural Networkscited by 231
- 2018Constrained Graph Variational Autoencoders for Molecule Designcited by 185
- 2017Simple and Effective Multi-Paragraph Reading Comprehensioncited by 120
- 2018Graphite: Iterative Generative Modeling of Graphscited by 112
- 2018Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoderscited by 74
- 2020GraphGen: A Scalable Approach to Domain-agnostic Labeled Graph Generationcited by 66
- 2018Tracking State Changes in Procedural Text: A Challenge Dataset and Models for Process Paragraph Comprehensioncited by 62
- 2017Simulating Action Dynamics with Neural Process Networkscited by 53
- 2016Tracking the World State with Recurrent Entity Networkscited by 51
- 2020CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Trainingcited by 38
- 2021Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Modelscited by 29
- 2018DEFactor: Differentiable Edge Factorization-based Probabilistic Graph Generationcited by 24
- 2020A Deep Generative Model for Fragment-Based Molecule Generationcited by 24
- 2019An Approach for Process Model Extraction By Multi-Grained Text Classificationcited by 16
- 2020Edge-based sequential graph generation with recurrent neural networkscited by 16
- 2022Learning Program Representations for Food Images and Cooking Recipescited by 16
- 2019Graph Generation with Variational Recurrent Neural Networkcited by 7
- 2019Decoding Molecular Graph Embeddings with Reinforcement Learningcited by 6
- 2019Adversarial Learned Molecular Graph Inference and Generationcited by 2
- 2022Procedural Text Understanding via Scene-Wise Evolutioncited by 1
Built on by
Not cited yet.