From Sentence to Action: Splitting AMR Graphs for Recipe Instructions

Katharina Stein; Lucia Donatelli; Alexander Koller

From Sentence to Action: Splitting AMR Graphs for Recipe Instructions

Katharina Stein
, Lucia Donatelli
, Alexander Koller

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Accurately interpreting the relationships between actions in a recipe text is essential to successful recipe completion. We explore using Abstract Meaning Representation (AMR) to represent recipe instructions, abstracting away from syntax and sentence structure that may order recipe actions in arbitrary ways. We present an algorithm to split sentence-level AMRs into action-level AMRs for individual cooking steps. Our approach provides an automatic way to derive fine-grained AMR representations of actions in cooking recipes and can be a useful tool for downstream, instructional tasks.

Original language	English
Title of host publication	Proceedings of the Fourth International Workshop on Designing Meaning Representations
Editors	Julia Bonn, Nianwen Xue
Publisher	Association for Computational Linguistics (ACL)
Pages	52-67
Number of pages	16
ISBN (Electronic)	9781959429654
Publication status	Published - 2023
Event	4th InternationalWorkshop on Designing Meaning Representations, DMR 2023 - Nancy, France Duration: 20 Jun 2023 → 23 Jun 2023

Conference

Conference	4th InternationalWorkshop on Designing Meaning Representations, DMR 2023
Country/Territory	France
City	Nancy
Period	20/06/23 → 23/06/23

Bibliographical note

Publisher Copyright:
©2023 Association for Computational Linguistics

Access to Document

https://aclanthology.org/2023.dmr-1.6/

Persistent URL (handle)

Persistent link

Cite this

@inproceedings{8f0b48649f0349ab83863ec87c1c311e,

title = "From Sentence to Action: Splitting AMR Graphs for Recipe Instructions",

abstract = "Accurately interpreting the relationships between actions in a recipe text is essential to successful recipe completion. We explore using Abstract Meaning Representation (AMR) to represent recipe instructions, abstracting away from syntax and sentence structure that may order recipe actions in arbitrary ways. We present an algorithm to split sentence-level AMRs into action-level AMRs for individual cooking steps. Our approach provides an automatic way to derive fine-grained AMR representations of actions in cooking recipes and can be a useful tool for downstream, instructional tasks.",

author = "Katharina Stein and Lucia Donatelli and Alexander Koller",

note = "Publisher Copyright: {\textcopyright}2023 Association for Computational Linguistics; 4th InternationalWorkshop on Designing Meaning Representations, DMR 2023 ; Conference date: 20-06-2023 Through 23-06-2023",

year = "2023",

language = "English",

pages = "52--67",

editor = "Julia Bonn and Nianwen Xue",

booktitle = "Proceedings of the Fourth International Workshop on Designing Meaning Representations",

publisher = "Association for Computational Linguistics (ACL)",

address = "United States",

}

Stein, K, Donatelli, L & Koller, A 2023, From Sentence to Action: Splitting AMR Graphs for Recipe Instructions. in J Bonn & N Xue (eds), Proceedings of the Fourth International Workshop on Designing Meaning Representations. Association for Computational Linguistics (ACL), pp. 52-67, 4th InternationalWorkshop on Designing Meaning Representations, DMR 2023, Nancy, France, 20/06/23. <https://aclanthology.org/2023.dmr-1.6/>

From Sentence to Action: Splitting AMR Graphs for Recipe Instructions. / Stein, Katharina; Donatelli, Lucia; Koller, Alexander.
Proceedings of the Fourth International Workshop on Designing Meaning Representations. ed. / Julia Bonn; Nianwen Xue. Association for Computational Linguistics (ACL), 2023. p. 52-67.

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - From Sentence to Action

T2 - 4th InternationalWorkshop on Designing Meaning Representations, DMR 2023

AU - Stein, Katharina

AU - Donatelli, Lucia

AU - Koller, Alexander

PY - 2023

Y1 - 2023

N2 - Accurately interpreting the relationships between actions in a recipe text is essential to successful recipe completion. We explore using Abstract Meaning Representation (AMR) to represent recipe instructions, abstracting away from syntax and sentence structure that may order recipe actions in arbitrary ways. We present an algorithm to split sentence-level AMRs into action-level AMRs for individual cooking steps. Our approach provides an automatic way to derive fine-grained AMR representations of actions in cooking recipes and can be a useful tool for downstream, instructional tasks.

AB - Accurately interpreting the relationships between actions in a recipe text is essential to successful recipe completion. We explore using Abstract Meaning Representation (AMR) to represent recipe instructions, abstracting away from syntax and sentence structure that may order recipe actions in arbitrary ways. We present an algorithm to split sentence-level AMRs into action-level AMRs for individual cooking steps. Our approach provides an automatic way to derive fine-grained AMR representations of actions in cooking recipes and can be a useful tool for downstream, instructional tasks.

UR - https://www.scopus.com/pages/publications/85179224334

UR - https://www.scopus.com/pages/publications/85179224334#tab=citedBy

M3 - Conference contribution

AN - SCOPUS:85179224334

SP - 52

EP - 67

BT - Proceedings of the Fourth International Workshop on Designing Meaning Representations

A2 - Bonn, Julia

A2 - Xue, Nianwen

PB - Association for Computational Linguistics (ACL)

Y2 - 20 June 2023 through 23 June 2023

ER -

From Sentence to Action: Splitting AMR Graphs for Recipe Instructions

Abstract

Conference

Bibliographical note

Access to Document

Persistent URL (handle)

Other files and links

Cite this