Goal-Oriented Script Construction
Not on the map. Why?
Abstract (arXiv)
The knowledge of scripts, common chains of events in stereotypical scenarios, is a valuable asset for task-oriented natural language understanding systems. We propose the Goal-Oriented Script Construction task, where a model produces a sequence of steps to accomplish a given goal. We pilot our task on the first multilingual script learning dataset supporting 18 languages collected from wikiHow, a website containing half a million how-to articles. For baselines, we consider both a generation-based approach using a language model and a retrieval-based approach by first retrieving the relevant steps from a large candidate pool and then ordering them. We show that our task is practical, feasible but challenging for state-of-the-art Transformer models, and that our methods can be readily deployed for various other datasets and domains with decent zero-shot performance.
Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 16 of its 50 references that are in the map. First posted on arXiv 28 Jul 2021.
Builds on
16 of 50 references.
References · 16
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
- 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
- 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
- 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
- 2018Hierarchical Neural Story Generationcited by 1,182
- 2018WikiHow: A Large Scale Text Summarization Datasetcited by 203
- 2020WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarizationcited by 154
- 2018RecipeQA: A Challenge Dataset for Multimodal Comprehension of Cooking Recipescited by 74
- 2020MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Modelscited by 74
- 2020Reasoning about Goals, Steps, and Temporal Ordering with WikiHowcited by 66
- 2020Analogous Process Structure Induction for Sub-event Sequence Predictioncited by 26
4 more
- 2019Learning Household Task Knowledge from WikiHow Descriptionscited by 15
- 2016Using Sentence-Level LSTM Language Models for Script Inferencecited by 10
- 2017Sequence to Sequence Learning for Event Predictioncited by 9
- 2017Aligning Script Events with Narrative Textscited by 2
Built on by
Citing papers per year: 2021: 3; 2022: 6; 2023: 10; 2024: 6; 2025: 4; 2026: 1.
30 papers.
Sort:
By area:
- 2023Distilling Script Knowledge from Large Language Models for Constrained Language Planningcited by 45
- 2022Neuro-Symbolic Procedural Planning with Commonsense Promptingcited by 28
- 2025Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarkscited by 26
- 2023Causal Reasoning of Entities and Events in Procedural Textscited by 23
- 2022Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Datacited by 22
- 2021What do Large Language Models Learn about Scripts?cited by 19
- 2024On the Limit of Language Models as Planning Formalizerscited by 17
- 2021Salience-Aware Event Chain Modeling for Narrative Understandingcited by 14
- 2024PDDLEGO: Iterative Planning in Textual Environmentscited by 14
- 2021Induce, Edit, Retrieve: Language Grounded Multimodal Schema for Instructional Video Retrievalcited by 13
- 2025NarraBench: A Comprehensive Framework for Narrative Benchmarkingcited by 13
- 2022Multimedia Generative Script Learning for Task Planningcited by 12
18 more
- 2022SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controllercited by 10
- 2024CaT-BENCH: Benchmarking Language Model Understanding of Causal and Temporal Dependencies in Planscited by 10
- 2022Reasoning about Procedures with Natural Language Processing: A Tutorialcited by 8
- 2023OpenPI2.0: An Improved Dataset for Entity Tracking in Textscited by 8
- 2023Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generationcited by 7
- 2023Unsupervised Task Graph Generation from Instructional Video Transcriptscited by 6
- 2023Rewriting the Script: Adapting Text Instructions for Voice Interactioncited by 5
- 2023Tailoring with Targeted Precision: Edit-Based Agents for Open-Domain Procedure Customizationcited by 5
- 2023Non-Sequential Graph Script Induction via Multimedia Groundingcited by 4
- 2024WorldAPIs: The World Is Worth How Many APIs? A Thought Experimentcited by 4
- 2024PAGED: A Benchmark for Procedural Graphs Extraction from Documentscited by 4
- 2022Incorporating Task-specific Concept Knowledge into Script Learningcited by 3
- 2023Choice-75: A Dataset on Decision Branching in Script Learningcited by 2
- 2023MULTISCRIPT: Multimodal Script Learning for Supporting Open Domain Everyday Taskscited by 2
- 2024SAGA: A Participant-specific Examination of Story Alternatives and Goal Applicability for a Deeper Understanding of Complex Eventscited by 2
- 2025Iterative Formalization and Planning in Partially Observable Environmentscited by 1
- 2025ScEdit: Script-based Assessment of Knowledge Editingcited by 1
- 2026The Imperfective Paradox in Large Language Modelscited by 1
- 2026The Imperfective Paradox in Large Language Models14 Jan 2026
- 2025NarraBench: A Comprehensive Framework for Narrative Benchmarking10 Oct 2025
- 2025ScEdit: Script-based Assessment of Knowledge Editing29 May 2025
- 2025Iterative Formalization and Planning in Partially Observable Environments19 May 2025
- 2025Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks26 Apr 2025
- 2024On the Limit of Language Models as Planning Formalizers13 Dec 2024
- 2024SAGA: A Participant-specific Examination of Story Alternatives and Goal Applicability for a Deeper Understanding of Complex Events11 Aug 2024
- 2024PAGED: A Benchmark for Procedural Graphs Extraction from Documents7 Aug 2024
- 2024WorldAPIs: The World Is Worth How Many APIs? A Thought Experiment10 Jul 2024
- 2024CaT-BENCH: Benchmarking Language Model Understanding of Causal and Temporal Dependencies in Plans22 Jun 2024
- 2024PDDLEGO: Iterative Planning in Textual Environments30 May 2024
- 2023Tailoring with Targeted Precision: Edit-Based Agents for Open-Domain Procedure Customization16 Nov 2023
18 more
- 2023MULTISCRIPT: Multimodal Script Learning for Supporting Open Domain Everyday Tasks8 Oct 2023
- 2023Choice-75: A Dataset on Decision Branching in Script Learning21 Sep 2023
- 2023Rewriting the Script: Adapting Text Instructions for Voice Interaction16 Jun 2023
- 2023Non-Sequential Graph Script Induction via Multimedia Grounding27 May 2023
- 2023OpenPI2.0: An Improved Dataset for Entity Tracking in Texts24 May 2023
- 2023Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generation18 May 2023
- 2023Distilling Script Knowledge from Large Language Models for Constrained Language Planning9 May 2023
- 2023Unsupervised Task Graph Generation from Instructional Video Transcripts17 Feb 2023
- 2023Causal Reasoning of Entities and Events in Procedural Texts26 Jan 2023
- 2022SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controller13 Oct 2022
- 2022Incorporating Task-specific Concept Knowledge into Script Learning31 Aug 2022
- 2022Multimedia Generative Script Learning for Task Planning25 Aug 2022
- 2022Neuro-Symbolic Procedural Planning with Commonsense Prompting6 Jun 2022
- 2022Reasoning about Procedures with Natural Language Processing: A Tutorial16 May 2022
- 2022Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Data14 Mar 2022
- 2021What do Large Language Models Learn about Scripts?27 Dec 2021
- 2021Induce, Edit, Retrieve: Language Grounded Multimodal Schema for Instructional Video Retrieval17 Nov 2021
- 2021Salience-Aware Event Chain Modeling for Narrative Understanding22 Sep 2021
- 2023Distilling Script Knowledge from Large Language Models for Constrained Language Planningcited by 45
- 2022Neuro-Symbolic Procedural Planning with Commonsense Promptingcited by 28
- 2025Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarkscited by 26
- 2022Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Datacited by 22
- 2021What do Large Language Models Learn about Scripts?cited by 19
- 2024On the Limit of Language Models as Planning Formalizerscited by 17
- 2021Salience-Aware Event Chain Modeling for Narrative Understandingcited by 14
- 2024PDDLEGO: Iterative Planning in Textual Environmentscited by 14
- 2021Induce, Edit, Retrieve: Language Grounded Multimodal Schema for Instructional Video Retrievalcited by 13
- 2025NarraBench: A Comprehensive Framework for Narrative Benchmarkingcited by 13
- 2022Multimedia Generative Script Learning for Task Planningcited by 12
- 2022SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controllercited by 10
12 most cited of 27 All 27 (JSON)
- 2026The Imperfective Paradox in Large Language Models14 Jan 2026
- 2025NarraBench: A Comprehensive Framework for Narrative Benchmarking10 Oct 2025
- 2025ScEdit: Script-based Assessment of Knowledge Editing29 May 2025
- 2025Iterative Formalization and Planning in Partially Observable Environments19 May 2025
- 2025Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks26 Apr 2025
- 2024On the Limit of Language Models as Planning Formalizers13 Dec 2024
- 2024SAGA: A Participant-specific Examination of Story Alternatives and Goal Applicability for a Deeper Understanding of Complex Events11 Aug 2024
- 2024PAGED: A Benchmark for Procedural Graphs Extraction from Documents7 Aug 2024
- 2024CaT-BENCH: Benchmarking Language Model Understanding of Causal and Temporal Dependencies in Plans22 Jun 2024
- 2024PDDLEGO: Iterative Planning in Textual Environments30 May 2024
- 2023MULTISCRIPT: Multimodal Script Learning for Supporting Open Domain Everyday Tasks8 Oct 2023
- 2023Choice-75: A Dataset on Decision Branching in Script Learning21 Sep 2023
12 newest of 27 All 27 (JSON)