# Incorporating Commonsense Knowledge into Story Ending Generation via Heterogeneous Graph Networks

arXiv: https://arxiv.org/abs/2201.12538 · HTML: https://mlsanity.com/paper/2201.12538/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 29 Jan 2022.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [Deep Biaffine Attention for Neural Dependency Parsing](https://mlsanity.com/paper/1611.01734/) (2016)
- [Plan-And-Write: Towards Better Automatic Storytelling](https://mlsanity.com/paper/1811.05701/) (2018)
- [WhiteningBERT: An Easy Unsupervised Sentence Embedding Approach](https://mlsanity.com/paper/2104.01767/) (2021)
- [Event Representations for Automated Story Generation with Deep Neural Nets](https://mlsanity.com/paper/1706.01331/) (2017)
- [Narrative Planning: Balancing Plot and Character](https://mlsanity.com/paper/1401.3841/) (2014)
- [Story Ending Generation with Incremental Encoding and Commonsense Knowledge](https://mlsanity.com/paper/1808.10113/) (2018)
- [Controllable Neural Story Plot Generation via Reward Shaping](https://mlsanity.com/paper/1809.10736/) (2018)
- [A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation](https://mlsanity.com/paper/1808.06945/) (2018)
- [Dialogue Discourse-Aware Graph Model and Data Augmentation for Meeting Summarization](https://mlsanity.com/paper/2012.03502/) (2020)
- [Incorporating Commonsense Knowledge into Abstractive Dialogue Summarization via Heterogeneous Graph Networks](https://mlsanity.com/paper/2010.10044/) (2020)
- [From Plots to Endings: A Reinforced Pointer Generator for Story Ending Generation](https://mlsanity.com/paper/1901.03459/) (2019)
- [WriterForcing: Generating more interesting story endings](https://mlsanity.com/paper/1907.08259/) (2019)

## Built on by (most cited first, 6 of 6)

- [Open-world Story Generation with Structured Knowledge Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2212.04634/) (2022)
- [Long-Document Cross-Lingual Summarization](https://mlsanity.com/paper/2212.00586/) (2022)
- [Probing Simile Knowledge from Pre-trained Language Models](https://mlsanity.com/paper/2204.12807/) (2022)
- [RT-KGD: Relation Transition Aware Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2207.08212/) (2022)
- [Snowman: A Million-scale Chinese Commonsense Knowledge Graph Distilled from Foundation Model](https://mlsanity.com/paper/2306.10241/) (2023)
- [Beyond Direct Generation: A Decomposed Approach to Well-Crafted Screenwriting with LLMs](https://mlsanity.com/paper/2510.23163/) (2025)

## Abstract (arXiv)

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.