Summary of Discourse-aware In-context Learning For Temporal Expression Normalization, by Akash Kumar Gautam et al.
Discourse-Aware In-Context Learning for Temporal Expression Normalization
by Akash Kumar Gautam, Lukas Lange, Jannik Strötgen
First submitted to arxiv on: 11 Apr 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 The proposed paper explores the application of large language models (LLMs) in temporal expression normalization using in-context learning. The authors investigate various sample selection strategies to retrieve relevant examples and leverage LLM knowledge without training the model. By employing a window-based prompt design approach, they achieve competitive results for TE normalization across sentences, particularly excelling in non-standard settings by dynamically including relevant examples during inference. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper uses large language models to help with temporal expression normalization, which is important for making sense of text that talks about dates and times. The researchers tested different ways of choosing the right examples to learn from and found a method that works well, even when the situation isn’t common or typical. |
Keywords
* Artificial intelligence * Inference * Prompt
