<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mahon-vogel-2023-proof">
    <titleInfo>
        <title>The Proof is in the Pudding: Using Automated Theorem Proving to Generate Cooking Recipes</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Louis</namePart>
        <namePart type="family">Mahon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Carl</namePart>
        <namePart type="family">Vogel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Journal for Language Technology and Computational Linguistics, Vol. 36 No. 2</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christian</namePart>
            <namePart type="family">Wartena</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>German Society for Computational Lingustics and Language Technology</publisher>
            <place>
                <placeTerm type="text">unknown</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper presents FASTFOOD, a rule-based natural language generation (NLG) program for cooking recipes. We consider the representation of cooking recipes as discourse representation, because the meaning of each sentence needs to consider the context of the others. Our discourse representation system is based on states of affairs and transtions between states of affairs, and does not use discourse referents. Recipes are generated by using an automated theorem-proving procedure to select the ingredients and instructions, with ingredients corresponding to axioms and instructions to implications. FASTFOOD also contains a temporal optimization module which can rearrange the recipe to make it more time efficient for the user, e.g. the recipe specifies to chop the vegetables while the rice is boiling. The system is described in detail, including the decision to forgo discourse referents and how plausible representations of nouns and verbs emerge purely as a by-product of the practical requirements of efficiently representing recipe content. A comparison is then made with existing recipe generation systems, NLG systems more generally, and automated theorem provers.</abstract>
    <identifier type="citekey">mahon-vogel-2023-proof</identifier>
    <identifier type="doi">10.21248/jlcl.36.2023.233</identifier>
    <location>
        <url>https://aclanthology.org/2023.jlcl-2.2</url>
    </location>
    <part>
        <date>2023-05</date>
        <extent unit="page">
            <start>29</start>
            <end>85</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T The Proof is in the Pudding: Using Automated Theorem Proving to Generate Cooking Recipes
%A Mahon, Louis
%A Vogel, Carl
%Y Wartena, Christian
%S Journal for Language Technology and Computational Linguistics, Vol. 36 No. 2
%D 2023
%8 May
%I German Society for Computational Lingustics and Language Technology
%C unknown
%F mahon-vogel-2023-proof
%X This paper presents FASTFOOD, a rule-based natural language generation (NLG) program for cooking recipes. We consider the representation of cooking recipes as discourse representation, because the meaning of each sentence needs to consider the context of the others. Our discourse representation system is based on states of affairs and transtions between states of affairs, and does not use discourse referents. Recipes are generated by using an automated theorem-proving procedure to select the ingredients and instructions, with ingredients corresponding to axioms and instructions to implications. FASTFOOD also contains a temporal optimization module which can rearrange the recipe to make it more time efficient for the user, e.g. the recipe specifies to chop the vegetables while the rice is boiling. The system is described in detail, including the decision to forgo discourse referents and how plausible representations of nouns and verbs emerge purely as a by-product of the practical requirements of efficiently representing recipe content. A comparison is then made with existing recipe generation systems, NLG systems more generally, and automated theorem provers.
%R 10.21248/jlcl.36.2023.233
%U https://aclanthology.org/2023.jlcl-2.2
%U https://doi.org/10.21248/jlcl.36.2023.233
%P 29-85

Markdown (Informal)

[The Proof is in the Pudding: Using Automated Theorem Proving to Generate Cooking Recipes](https://aclanthology.org/2023.jlcl-2.2) (Mahon & Vogel, JLCL 2023)

• The Proof is in the Pudding: Using Automated Theorem Proving to Generate Cooking Recipes (Mahon & Vogel, JLCL 2023)

ACL

• Louis Mahon and Carl Vogel. 2023. The Proof is in the Pudding: Using Automated Theorem Proving to Generate Cooking Recipes. In Journal for Language Technology and Computational Linguistics, Vol. 36 No. 2, pages 29–85, unknown. German Society for Computational Lingustics and Language Technology.