@inproceedings{nevens-etal-2024-benchmark,
title = "A Benchmark for Recipe Understanding in Artificial Agents",
author = "Nevens, Jens and
de Haes, Robin and
Ringe, Rachel and
Pomarlan, Mihai and
Porzel, Robert and
Beuls, Katrien and
van Eecke, Paul",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.3",
pages = "22--42",
abstract = "This paper introduces a novel benchmark that has been designed as a test bed for evaluating whether artificial agents are able to understand how to perform everyday activities, with a focus on the cooking domain. Understanding how to cook recipes is a highly challenging endeavour due to the underspecified and grounded nature of recipe texts, combined with the fact that recipe execution is a knowledge-intensive and precise activity. The benchmark comprises a corpus of recipes, a procedural semantic representation language of cooking actions, qualitative and quantitative kitchen simulators, and a standardised evaluation procedure. Concretely, the benchmark task consists in mapping a recipe formulated in natural language to a set of cooking actions that is precise enough to be executed in the simulated kitchen and yields the desired dish. To overcome the challenges inherent to recipe execution, this mapping process needs to incorporate reasoning over the recipe text, the state of the simulated kitchen environment, common-sense knowledge, knowledge of the cooking domain, and the action space of a virtual or robotic chef. This benchmark thereby addresses the growing interest in human-centric systems that combine natural language processing and situated reasoning to perform everyday activities.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nevens-etal-2024-benchmark">
<titleInfo>
<title>A Benchmark for Recipe Understanding in Artificial Agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jens</namePart>
<namePart type="family">Nevens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robin</namePart>
<namePart type="family">de Haes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Ringe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihai</namePart>
<namePart type="family">Pomarlan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Porzel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katrien</namePart>
<namePart type="family">Beuls</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">van Eecke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces a novel benchmark that has been designed as a test bed for evaluating whether artificial agents are able to understand how to perform everyday activities, with a focus on the cooking domain. Understanding how to cook recipes is a highly challenging endeavour due to the underspecified and grounded nature of recipe texts, combined with the fact that recipe execution is a knowledge-intensive and precise activity. The benchmark comprises a corpus of recipes, a procedural semantic representation language of cooking actions, qualitative and quantitative kitchen simulators, and a standardised evaluation procedure. Concretely, the benchmark task consists in mapping a recipe formulated in natural language to a set of cooking actions that is precise enough to be executed in the simulated kitchen and yields the desired dish. To overcome the challenges inherent to recipe execution, this mapping process needs to incorporate reasoning over the recipe text, the state of the simulated kitchen environment, common-sense knowledge, knowledge of the cooking domain, and the action space of a virtual or robotic chef. This benchmark thereby addresses the growing interest in human-centric systems that combine natural language processing and situated reasoning to perform everyday activities.</abstract>
<identifier type="citekey">nevens-etal-2024-benchmark</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.3</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>22</start>
<end>42</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Benchmark for Recipe Understanding in Artificial Agents
%A Nevens, Jens
%A de Haes, Robin
%A Ringe, Rachel
%A Pomarlan, Mihai
%A Porzel, Robert
%A Beuls, Katrien
%A van Eecke, Paul
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F nevens-etal-2024-benchmark
%X This paper introduces a novel benchmark that has been designed as a test bed for evaluating whether artificial agents are able to understand how to perform everyday activities, with a focus on the cooking domain. Understanding how to cook recipes is a highly challenging endeavour due to the underspecified and grounded nature of recipe texts, combined with the fact that recipe execution is a knowledge-intensive and precise activity. The benchmark comprises a corpus of recipes, a procedural semantic representation language of cooking actions, qualitative and quantitative kitchen simulators, and a standardised evaluation procedure. Concretely, the benchmark task consists in mapping a recipe formulated in natural language to a set of cooking actions that is precise enough to be executed in the simulated kitchen and yields the desired dish. To overcome the challenges inherent to recipe execution, this mapping process needs to incorporate reasoning over the recipe text, the state of the simulated kitchen environment, common-sense knowledge, knowledge of the cooking domain, and the action space of a virtual or robotic chef. This benchmark thereby addresses the growing interest in human-centric systems that combine natural language processing and situated reasoning to perform everyday activities.
%U https://aclanthology.org/2024.lrec-main.3
%P 22-42
Markdown (Informal)
[A Benchmark for Recipe Understanding in Artificial Agents](https://aclanthology.org/2024.lrec-main.3) (Nevens et al., LREC-COLING 2024)
ACL
- Jens Nevens, Robin de Haes, Rachel Ringe, Mihai Pomarlan, Robert Porzel, Katrien Beuls, and Paul van Eecke. 2024. A Benchmark for Recipe Understanding in Artificial Agents. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 22–42, Torino, Italia. ELRA and ICCL.