Summary of When and Where Did It Happen? An Encoder-decoder Model to Identify Scenario Context, by Enrique Noriega-atala et al.
When and Where Did it Happen? An Encoder-Decoder Model to Identify Scenario Context
by Enrique Noriega-Atala, Robert Vacareanu, Salena Torres Ashton, Adarsh Pyarelal, Clayton T. Morrison, Mihai Surdeanu
First submitted to arxiv on: 10 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 introduces a neural architecture specifically designed for generating scenario context, which involves identifying the location and time of an event or entity mentioned in text. This task is crucial for evaluating the validity of automated findings when aggregating them as knowledge graphs. The proposed approach uses a curated dataset of time and location annotations from epidemiology papers to train an encoder-decoder architecture. Additionally, the paper explores the use of data augmentation techniques during training. The results show that a fine-tuned encoder-decoder model outperforms pre-trained language models (LLMs) and semantic role labeling parsers in accurately predicting scenario information. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The research aims to improve automated information extraction by generating context for scenario understanding. A neural network is trained on a dataset of time and location annotations from epidemiology papers. The goal is to identify the relevant location and time of an event or entity mentioned in text. The results show that fine-tuning a model for this task leads to better performance compared to using pre-trained models. |
Keywords
» Artificial intelligence » Data augmentation » Encoder decoder » Fine tuning » Neural network
