Summary of Fine-grained Modeling Of Narrative Context: a Coherence Perspective Via Retrospective Questions, by Liyan Xu et al.
Fine-Grained Modeling of Narrative Context: A Coherence Perspective via Retrospective Questions
by Liyan Xu, Jiangnan Li, Mo Yu, Jie Zhou
First submitted to arxiv on: 21 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents a novel approach to understanding narratives, building on the idea that individual passages within stories are more connected than standalone. To achieve this, the authors introduce NarCo, a graph-based model that captures context-dependent relationships between narrative snippets. This fine-grained modeling enables various downstream tasks to leverage the coherence captured by NarCo. The paper demonstrates the effectiveness of NarCo through three studies, each exploring different aspects of the graph’s properties and utility. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research is about making computers better at understanding stories. Right now, computers are good at reading individual sentences or passages, but they struggle to understand how those parts fit together to tell a story. The authors came up with a new way to represent this connection between different parts of a story, called NarCo. This helps computers understand stories in a more human-like way, which can be useful for tasks like answering questions about what happened in the story. |
