When and Where Did it Happen? An Encoder-Decoder Model to Identify Scenario Context

TL;DR

This paper presents a neural encoder-decoder model trained on epidemiology texts to accurately identify relevant location and time information for events or entities, aiding knowledge graph construction.

Contribution

It introduces a specialized neural architecture and dataset for scenario context generation, outperforming general LLMs and semantic parsers in this task.

Findings

Fine-tuned model surpasses out-of-the-box LLMs in accuracy

Data augmentation improves model performance

Model effectively extracts scenario context from epidemiology texts

Abstract

We introduce a neural architecture finetuned for the task of scenario context generation: The relevant location and time of an event or entity mentioned in text. Contextualizing information extraction helps to scope the validity of automated finings when aggregating them as knowledge graphs. Our approach uses a high-quality curated dataset of time and location annotations in a corpus of epidemiology papers to train an encoder-decoder architecture. We also explored the use of data augmentation techniques during training. Our findings suggest that a relatively small fine-tuned encoder-decoder model performs better than out-of-the-box LLMs and semantic role labeling parsers to accurate predict the relevant scenario information of a particular entity or event.