Summary of Rst-lora: a Discourse-aware Low-rank Adaptation For Long Document Abstractive Summarization, by Dongqi Liu and Vera Demberg
RST-LoRA: A Discourse-Aware Low-Rank Adaptation for Long Document Abstractive Summarization
by Dongqi Liu, Vera Demberg
First submitted to arxiv on: 1 May 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); 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 In this paper, researchers explore ways to improve long document summarization by incorporating a theory called Rhetorical Structure Theory (RST) into a model called LoRA. They propose four new variants of the LoRA model that explicitly use RST to analyze text structure and importance. The authors evaluate their approach using various metrics and show that it outperforms previous methods, including state-of-the-art models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps computers understand how to summarize long documents better by combining two ideas: a theory about how sentences relate to each other (Rhetorical Structure Theory) and a way to fine-tune computer models for summarization tasks. By using this combination, the researchers created new models that can summarize texts more accurately than before. |
Keywords
» Artificial intelligence » Lora » Summarization
