COINS: Dynamically Generating COntextualized Inference Rules for Narrative Story Completion

Abstract

Despite recent successes of large pre-trained language models in solving reasoning tasks, their inference capabilities remain opaque. We posit that such models can be made more interpretable by explicitly generating interim inference rules, and using them to guide the generation of task-specific textual outputs. In this paper we present COINS, a recursive inference framework that i) iteratively reads context sentences, ii) dynamically generates contextualized inference rules, encodes them, and iii) uses them to guide task-specific output generation. We apply COINS to a Narrative Story Completion task that asks a model to complete a story with missing sentences, to produce a coherent story with plausible logical connections, causal relationships, and temporal dependencies. By modularizing inference and sentence generation steps in a recurrent model, we aim to make reasoning steps and their effects on next sentence generation transparent. Our automatic and manual evaluations show that the model generates better story sentences than SOTA baselines, especially in terms of coherence. We further demonstrate improved performance over strong pre-trained LMs in generating commonsense inference rules. The recursive nature of COINS holds the potential for controlled generation of longer sequences.

Understanding the Limits of Artificial Intelligence for Warfighters: Volume 4, Wargames

“…• procedurally generating gaming environments, such as geographic terrain, urban environments, maps, and interstate systems 62 • creating simple game-playing agents that could be used to provide players with interactive tutorials regarding game mechanics and objectives • creating or completing scenario details and background materials that provide players with narrative detail regarding the game environment and player motives. 63 Although all game types have the potential to use AI in these capacities during preparation, it should be noted that innovation and systems exploration applications are less likely to pose questions that are as well specified, making their use less likely.…”

LOT: A Story-Centric Benchmark for Evaluating Chinese Long Text Understanding and Generation

“…Dataset Construction Prior studies (Wang and Wan, 2019;Paul and Frank, 2021) automatically constructed datasets for this task based on existing datasets by randomly removing one sentence from a story. However, as shown in Table 4, not all sentences in a story can be reasoned only based on the context and common sense.…”

Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey

“…These intermediate inference rules provide are another form of model explanation and provide insights for improving model performance. Paul and Frank (2021) exploit GPT-2 to perform narrative story completion: given a few sentences of a story, the goal is to complete the story using sentences that logically follow the narrative in the given incomplete story. In an incremental generation method, each step seeks to generate a contextualized inference rule conditioned on the current incomplete story.…”