Goal-Oriented Procedure Generation.pdf

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.

Goal-Oriented Script Construction Qing Lyu∗ Li Zhang∗ Chris Callison-Burch University of Pennsylvania {lyuqing,zharry,ccb}@seas.upenn.edu Abstract The knowledge of scripts, common chains of arXiv:2107.13189v3 [cs.CL] 31 Aug 2021…

related reading

• [2005.11401] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasksarxiv.org
• Language Models can Solve Computer Tasksarxiv.org
• [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
• [2005.14165] Language Models are Few-Shot Learnersarxiv.org
• 2026.mellm-1.2.pdfaclanthology.org
• [2608.20319] Inducing Task Models from Computer-Use Tracesarxiv.org
• Efficient Guided Generation for Large Language Modelsarxiv.org
• [2201.07207] Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentsarxiv.org
• Large language models are few-shot clinical information extractorsarxiv.org
• TOD-Bertarxiv.org
• [2603.05923] Learning Next Action Predictors from Human-Computer Interactionarxiv.org
• [2508.19227] Generative Interfaces for Language Modelsarxiv.org