Incorporating Commonsense Knowledge into Story Ending Generation via Heterogeneous Graph Networks

TL;DR

This paper introduces a novel heterogeneous graph network that explicitly models story context, commonsense knowledge, and multi-grained relations to improve story ending generation, achieving state-of-the-art results.

Contribution

The paper proposes a new heterogeneous graph network with auxiliary tasks for better story comprehension and ending generation, advancing the modeling of implicit knowledge.

Findings

Achieves new state-of-the-art performance on ROCStories Corpus.

Generates more reasonable and coherent story endings according to human evaluation.

Effectively utilizes commonsense knowledge and multi-grained relations for story understanding.

Abstract

Story ending generation is an interesting and challenging task, which aims to generate a coherent and reasonable ending given a story context. The key challenges of the task lie in how to comprehend the story context sufficiently and handle the implicit knowledge behind story clues effectively, which are still under-explored by previous work. In this paper, we propose a Story Heterogeneous Graph Network (SHGN) to explicitly model both the information of story context at different granularity levels and the multi-grained interactive relations among them. In detail, we consider commonsense knowledge, words and sentences as three types of nodes. To aggregate non-local information, a global node is also introduced. Given this heterogeneous graph network, the node representations are updated through graph propagation, which adequately utilizes commonsense knowledge to facilitate story comprehension. Moreover, we design two auxiliary tasks to implicitly capture the sentiment trend and key events lie in the context. The auxiliary tasks are jointly optimized with the primary story ending generation task in a multi-task learning strategy. Extensive experiments on the ROCStories Corpus show that the developed model achieves new state-of-the-art performances. Human study further demonstrates that our model generates more reasonable story endings.