# Goal-Oriented Script Construction

arXiv: https://arxiv.org/abs/2107.13189 · HTML: https://mlsanity.com/paper/2107.13189/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 50 references that are in the map.
- First posted on arXiv 28 Jul 2021.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [WikiHow: A Large Scale Text Summarization Dataset](https://mlsanity.com/paper/1810.09305/) (2018)
- [WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization](https://mlsanity.com/paper/2010.03093/) (2020)
- [RecipeQA: A Challenge Dataset for Multimodal Comprehension of Cooking Recipes](https://mlsanity.com/paper/1809.00812/) (2018)
- [MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Models](https://mlsanity.com/paper/2010.00840/) (2020)
- [Reasoning about Goals, Steps, and Temporal Ordering with WikiHow](https://mlsanity.com/paper/2009.07690/) (2020)
- [Analogous Process Structure Induction for Sub-event Sequence Prediction](https://mlsanity.com/paper/2010.08525/) (2020)
- [Learning Household Task Knowledge from WikiHow Descriptions](https://mlsanity.com/paper/1909.06414/) (2019)
- [Using Sentence-Level LSTM Language Models for Script Inference](https://mlsanity.com/paper/1604.02993/) (2016)
- [Sequence to Sequence Learning for Event Prediction](https://mlsanity.com/paper/1709.06033/) (2017)
- [Aligning Script Events with Narrative Texts](https://mlsanity.com/paper/1710.05709/) (2017)

## Built on by (most cited first, 30 of 30)

- [Distilling Script Knowledge from Large Language Models for Constrained Language Planning](https://mlsanity.com/paper/2305.05252/) (2023)
- [Neuro-Symbolic Procedural Planning with Commonsense Prompting](https://mlsanity.com/paper/2206.02928/) (2022)
- [Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks](https://mlsanity.com/paper/2504.18838/) (2025)
- [Causal Reasoning of Entities and Events in Procedural Texts](https://mlsanity.com/paper/2301.10896/) (2023)
- [Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Data](https://mlsanity.com/paper/2203.07264/) (2022)
- [What do Large Language Models Learn about Scripts?](https://mlsanity.com/paper/2112.13834/) (2021)
- [On the Limit of Language Models as Planning Formalizers](https://mlsanity.com/paper/2412.09879/) (2024)
- [Salience-Aware Event Chain Modeling for Narrative Understanding](https://mlsanity.com/paper/2109.10475/) (2021)
- [PDDLEGO: Iterative Planning in Textual Environments](https://mlsanity.com/paper/2405.19793/) (2024)
- [Induce, Edit, Retrieve: Language Grounded Multimodal Schema for Instructional Video Retrieval](https://mlsanity.com/paper/2111.09276/) (2021)
- [NarraBench: A Comprehensive Framework for Narrative Benchmarking](https://mlsanity.com/paper/2510.09869/) (2025)
- [Multimedia Generative Script Learning for Task Planning](https://mlsanity.com/paper/2208.12306/) (2022)
- [CaT-BENCH: Benchmarking Language Model Understanding of Causal and Temporal Dependencies in Plans](https://mlsanity.com/paper/2406.15823/) (2024)
- [SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controller](https://mlsanity.com/paper/2210.06694/) (2022)
- [Reasoning about Procedures with Natural Language Processing: A Tutorial](https://mlsanity.com/paper/2205.07455/) (2022)
- [OpenPI2.0: An Improved Dataset for Entity Tracking in Texts](https://mlsanity.com/paper/2305.14603/) (2023)
- [Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generation](https://mlsanity.com/paper/2305.10907/) (2023)
- [Unsupervised Task Graph Generation from Instructional Video Transcripts](https://mlsanity.com/paper/2302.09173/) (2023)
- [Rewriting the Script: Adapting Text Instructions for Voice Interaction](https://mlsanity.com/paper/2306.09992/) (2023)
- [Tailoring with Targeted Precision: Edit-Based Agents for Open-Domain Procedure Customization](https://mlsanity.com/paper/2311.09510/) (2023)
- [Non-Sequential Graph Script Induction via Multimedia Grounding](https://mlsanity.com/paper/2305.17542/) (2023)
- [WorldAPIs: The World Is Worth How Many APIs? A Thought Experiment](https://mlsanity.com/paper/2407.07778/) (2024)
- [PAGED: A Benchmark for Procedural Graphs Extraction from Documents](https://mlsanity.com/paper/2408.03630/) (2024)
- [Incorporating Task-specific Concept Knowledge into Script Learning](https://mlsanity.com/paper/2209.00068/) (2022)
- [Choice-75: A Dataset on Decision Branching in Script Learning](https://mlsanity.com/paper/2309.11737/) (2023)
- [MULTISCRIPT: Multimodal Script Learning for Supporting Open Domain Everyday Tasks](https://mlsanity.com/paper/2310.04965/) (2023)
- [SAGA: A Participant-specific Examination of Story Alternatives and Goal Applicability for a Deeper Understanding of Complex Events](https://mlsanity.com/paper/2408.05793/) (2024)
- [Iterative Formalization and Planning in Partially Observable Environments](https://mlsanity.com/paper/2505.13126/) (2025)
- [ScEdit: Script-based Assessment of Knowledge Editing](https://mlsanity.com/paper/2505.23291/) (2025)
- [The Imperfective Paradox in Large Language Models](https://mlsanity.com/paper/2601.09373/) (2026)

## 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.