Summary of Deep Learning Based Named Entity Recognition Models For Recipes, by Mansi Goel et al.
Deep Learning Based Named Entity Recognition Models for Recipes
by Mansi Goel, Ayush Agarwal, Shubham Agrawal, Janak Kapuriya, Akhil Vamshi Konam, Rishabh Gupta, Shrey Rastogi, Niharika, Ganesh Bagler
First submitted to arxiv on: 27 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper focuses on developing automated protocols for recognizing named entities in recipe text. Named entity recognition is a technique used to extract information from unstructured or semi-structured data with known labels. The authors create three datasets: manually-annotated, augmented, and machine-annotated, consisting of ingredient phrases. They investigate different NER approaches, including statistical models, fine-tuning of deep learning-based language models, and few-shot prompting on large language models (LLMs). The results show that few-shot prompting on LLMs performs poorly, while the fine-tuned spaCy-transformer model achieves high macro-F1 scores across all three datasets. This research has implications for various applications, including information extraction and novel recipe generation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making computers better at understanding recipes. Recipes are special kinds of text that contain instructions on how to cook food. To help computers understand recipes, the authors create large collections of words that describe ingredients and cooking methods. They then test different ways that computers can learn from these words to recognize important information. The results show that one approach is much better than others at recognizing what’s important in a recipe. This research could lead to new tools for finding and sharing recipes online. |
Keywords
» Artificial intelligence » Deep learning » Few shot » Fine tuning » Named entity recognition » Ner » Prompting » Transformer
