Actionable Entities Recognition Benchmark for Interactive Fiction
This addresses the need for agents in interactive fiction to detect useful entities for narrative processing, though it is incremental as it builds on existing NER concepts.
The paper introduces Actionable Entities Recognition (AER), a new NLP task for identifying entities that protagonists can interact with to advance plots in interactive fiction, and presents a benchmark dataset of 5550 descriptions with actionable entities.
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.