Actionable Entities Recognition Benchmark for Interactive Fiction

TL;DR

This paper introduces Actionable Entities Recognition, a new NLP task for identifying entities in interactive fiction that could influence future plot development, supported by a new benchmark dataset.

Contribution

It defines the AER task, highlights its importance for interactive storytelling, and provides a new benchmark dataset for future research.

Findings

Validated AER on existing datasets

Created a new benchmark dataset with 5550 descriptions

Demonstrated potential impact on narrative processing systems

Abstract

This paper presents a new natural language processing task - Actionable Entities Recognition (AER) - recognition of entities that protagonists could interact with for further plot development. Though similar to classical Named Entity Recognition (NER), it has profound differences. In particular, it is crucial for interactive fiction, where the agent needs to detect entities that might be useful in the future. We also discuss if AER might be further helpful for the systems dealing with narrative processing since actionable entities profoundly impact the causal relationship in a story. We validate the proposed task on two previously available datasets and present a new benchmark dataset for the AER task that includes 5550 descriptions with one or more actionable entities.