# Improving Narrative Relationship Embeddings by Training with Additional Inverse-Relationship Constraints

arXiv: https://arxiv.org/abs/2212.11234 · HTML: https://mlsanity.com/paper/2212.11234/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 19 references that are in the map.
- First posted on arXiv 21 Dec 2022.

## Builds on (most cited first, 7 of 7)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [KG-BERT: BERT for Knowledge Graph Completion](https://mlsanity.com/paper/1909.03193/) (2019)
- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation](https://mlsanity.com/paper/1810.10147/) (2018)
- [Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks](https://mlsanity.com/paper/2012.08492/) (2020)
- [Mapping Text to Knowledge Graph Entities using Multi-Sense LSTMs](https://mlsanity.com/paper/1808.07724/) (2018)
- [Unsupervised Construction of Knowledge Graphs From Text and Code](https://mlsanity.com/paper/1908.09354/) (2019)

## Abstract (arXiv)

We consider the problem of embedding character-entity relationships from the reduced semantic space of narratives, proposing and evaluating the assumption that these relationships hold under a reflection operation. We analyze this assumption and compare the approach to a baseline state-of-the-art model with a unique evaluation that simulates efficacy on a downstream clustering task with human-created labels. Although our model creates clusters that achieve Silhouette scores of -.084, outperforming the baseline -.227, our analysis reveals that the models approach the task much differently and perform well on very different examples. We conclude that our assumption might be useful for specific types of data and should be evaluated on a wider range of tasks.