Summary of Timeline-based Sentence Decomposition with In-context Learning For Temporal Fact Extraction, by Jianhao Chen et al.
Timeline-based Sentence Decomposition with In-Context Learning for Temporal Fact Extraction
by Jianhao Chen, Haoyuan Ouyang, Junyang Ren, Wentao Ding, Wei Hu, Yuzhong Qu
First submitted to arxiv on: 16 May 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 novel approach to extract temporal facts from natural language text by introducing a timeline-based sentence decomposition strategy using large language models (LLMs) with in-context learning. The method, called TSDRE, combines the decomposition capabilities of LLMs with traditional fine-tuning of smaller pre-trained language models (PLMs). To evaluate TSDRE, the authors construct ComplexTRED, a complex temporal fact extraction dataset. Experimental results show that TSDRE achieves state-of-the-art performance on both HyperRED-Temporal and ComplexTRED datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about finding important events in text and understanding when they happened. Right now, there’s no good way to do this because previous methods can’t handle complex sentences. To fix this, the authors use a special kind of AI model that can understand timeline information. They also create a new dataset called ComplexTRED to test their method. The results show that it works really well! |
Keywords
» Artificial intelligence » Fine tuning
