Here are the dataset and codes for our ESANN 2022 paper "Attention-based Ingredient Parser".
As virtual personal assistants have now penetrated the consumer market, with products such as Siri and Alexa, the research community has produced several works on task-oriented dialogue tasks such as hotel booking, restaurant booking, and movie recommendation.
Applications of our ingredient parser model for conversational systems.
Assisting users to cook is one of these tasks that are expected to be solved by intelligent assistants, where ingredients and its corresponding attributes, such as name, unit, and quantity, should be provided to users precisely and promptly. To provide an engaged and successful conversational service to users for cooking tasks, we propose a new ingredient parsing model.
Model architecture.
To reproduce our result, please follow the instructions below:
You can skip this step since data/vocab.pkl
is provided.
cd data
wget https://nlp.stanford.edu/data/glove.42B.300d.zip
unzip glove.42B.300d.zip
cd ..
python train.py --seed 0 --path saved_model_path
python infer.py --path saved_model_path
python test.py --path saved_model_path
The source of the dataset is https://github.com/cosylabiiit/Recipedb-companion-data
.
ar_train.tsv
andar_test.tsv
are fromAllRecipes Food Corpus
;gk_train.tsv
andgk_test.tsv
are fromFOOD.com corpus
;ar_gk_train.tsv
andar_gk_test.tsv
are fromAllRecipes Food Corpus
andFOOD.com corpus
.
@inproceedings{Shi2022attention,
title = {Attention-based Ingredient Parser},
author = {Shi, Zhengxiang and Ni, Pin and Wang, Meihui and Kim, To Eun and Lipani, Aldo},
booktitle = {European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)},
url={https://doi.org/10.14428/esann/2022.ES2022-10},
year = {2022},
address = {Bruges, Belgium},
keywords = {Conversational System, Named Entity Recognition}
}