Summary of `keep It Together’: Enforcing Cohesion in Extractive Summaries by Simulating Human Memory, By Ronald Cardenas and Matthias Galle and Shay B. Cohen
`Keep it Together’: Enforcing Cohesion in Extractive Summaries by Simulating Human Memory
by Ronald Cardenas, Matthias Galle, Shay B. Cohen
First submitted to arxiv on: 16 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 proposes a novel approach to generating extractive summaries that balances informativeness and cohesion. Unlike traditional methods, which often prioritize one aspect over the other, this pipeline controls for redundancy in long inputs while selecting sentences that create cohesive ties between noun phrases. The authors use lexical chains to model human memory and ensure smooth topic transitions between sentences. Experimental results across various domains demonstrate that it is possible to extract highly informative and cohesive summaries using this approach. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us make better summaries of big texts by making sure they’re both helpful and easy to follow. Usually, summaries are just lists of sentences that don’t really connect with each other. But the new method in this paper makes sure those connections exist, so the summary flows smoothly from one idea to another. It works by using special “chains” of words to keep track of what’s being talked about and making sure those chains link up between sentences. The results show that this approach can create summaries that are both helpful and easy to understand. |
