# Assistive Recipe Editing through Critiquing

arXiv: https://arxiv.org/abs/2205.02454 · HTML: https://mlsanity.com/paper/2205.02454/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 45 references that are in the map.
- First posted on arXiv 5 May 2022.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Rationalizing Neural Predictions](https://mlsanity.com/paper/1606.04155/) (2016)
- [Interpretable Neural Predictions with Differentiable Binary Variables](https://mlsanity.com/paper/1905.08160/) (2019)
- [Simulating Action Dynamics with Neural Process Networks](https://mlsanity.com/paper/1711.05313/) (2017)
- [Generating Personalized Recipes from Historical User Preferences](https://mlsanity.com/paper/1909.00105/) (2019)
- [Inverse Cooking: Recipe Generation from Food Images](https://mlsanity.com/paper/1812.06164/) (2018)
- [Understanding Interlocking Dynamics of Cooperative Rationalization](https://mlsanity.com/paper/2110.13880/) (2021)
- [Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation](https://mlsanity.com/paper/1905.12926/) (2019)
- [RecipeGPT: Generative Pre-training Based Cooking Recipe Generation and Evaluation System](https://mlsanity.com/paper/2003.02498/) (2020)
- [Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints](https://mlsanity.com/paper/1809.01215/) (2018)
- [Rationalization through Concepts](https://mlsanity.com/paper/2105.04837/) (2021)
- [ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding](https://mlsanity.com/paper/2010.12148/) (2020)
- [SHARE: a System for Hierarchical Assistive Recipe Editing](https://mlsanity.com/paper/2105.08185/) (2021)
- [Interacting with Explanations through Critiquing](https://mlsanity.com/paper/2005.11067/) (2020)
- [Fast Multi-Step Critiquing for VAE-based Recommender Systems](https://mlsanity.com/paper/2105.00774/) (2021)
- [Multi-Step Critiquing User Interface for Recommender Systems](https://mlsanity.com/paper/2107.06416/) (2021)

## Built on by (most cited first, 2 of 2)

- [Cultural Adaptation of Recipes](https://mlsanity.com/paper/2310.17353/) (2023)
- [Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario](https://mlsanity.com/paper/2210.11431/) (2022)

## Abstract (arXiv)

There has recently been growing interest in the automatic generation of cooking recipes that satisfy some form of dietary restrictions, thanks in part to the availability of online recipe data. Prior studies have used pre-trained language models, or relied on small paired recipe data (e.g., a recipe paired with a similar one that satisfies a dietary constraint). However, pre-trained language models generate inconsistent or incoherent recipes, and paired datasets are not available at scale. We address these deficiencies with RecipeCrit, a hierarchical denoising auto-encoder that edits recipes given ingredient-level critiques. The model is trained for recipe completion to learn semantic relationships within recipes. Our work's main innovation is our unsupervised critiquing module that allows users to edit recipes by interacting with the predicted ingredients; the system iteratively rewrites recipes to satisfy users' feedback. Experiments on the Recipe1M recipe dataset show that our model can more effectively edit recipes compared to strong language-modeling baselines, creating recipes that satisfy user constraints and are more correct, serendipitous, coherent, and relevant as measured by human judges.