COINS: Dynamically Generating COntextualized Inference Rules for Narrative Story Completion

TL;DR

COINS introduces a recursive framework that explicitly generates and utilizes contextualized inference rules to improve narrative story completion, enhancing coherence and interpretability over existing models.

Contribution

The paper presents COINS, a novel recursive inference framework that dynamically generates and applies inference rules for story completion, improving coherence and interpretability.

Findings

COINS outperforms SOTA baselines in story coherence.

The model generates more plausible and logical story sentences.

COINS improves inference rule quality over strong pre-trained LMs.

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.