Summary of One2set + Large Language Model: Best Partners For Keyphrase Generation, by Liangying Shao et al.
One2set + Large Language Model: Best Partners for Keyphrase Generation
by Liangying Shao, Liang Zhang, Minlong Peng, Guoqi Ma, Hao Yue, Mingming Sun, Jinsong Su
First submitted to arxiv on: 4 Oct 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 The paper proposes a new approach to keyphrase generation (KPG), which involves decomposing the process into two steps: generating candidates using a one2set-based model and then selecting keyphrases from these candidates using a large language model (LLM). The authors identify limitations in existing KPG methods, including high recall but poor precision. They introduce an Optimal Transport-based assignment strategy to improve candidate generation and model keyphrase selection as a sequence labeling task to reduce redundant selections. Experimental results on multiple benchmark datasets demonstrate the framework’s superiority over state-of-the-art models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about making computers better at understanding what something is about by breaking it down into two steps. First, they generate lots of phrases related to the topic, and then they choose the most important ones. Right now, there are some problems with how we do this, like getting too many phrases that aren’t really important. The authors came up with a new way to do things that works better. They tried it out on different sets of data and showed that their method is much better than what’s been done before. |
Keywords
» Artificial intelligence » Large language model » Precision » Recall
