PyTorch-IE: Fast and Reproducible Prototyping for Information Extraction

TL;DR

PyTorch-IE is a flexible, reusable framework that simplifies the development of information extraction models by integrating diverse data types and supporting rapid, reproducible prototyping.

Contribution

It introduces a novel flexible data model and task modules that enhance reusability and decoupling in IE model development, supporting multiple data formats and libraries.

Findings

Enables swift prototyping of IE models.

Supports complex data structures and diverse data types.

Facilitates reproducibility and reusability in IE research.

Abstract

The objective of Information Extraction (IE) is to derive structured representations from unstructured or semi-structured documents. However, developing IE models is complex due to the need of integrating several subtasks. Additionally, representation of data among varied tasks and transforming datasets into task-specific model inputs presents further challenges. To streamline this undertaking for researchers, we introduce PyTorch-IE, a deep-learning-based framework uniquely designed to enable swift, reproducible, and reusable implementations of IE models. PyTorch-IE offers a flexible data model capable of creating complex data structures by integrating interdependent layers of annotations derived from various data types, like plain text or semi-structured text, and even images. We propose task modules to decouple the concerns of data representation and model-specific representations, thereby fostering greater flexibility and reusability of code. PyTorch-IE also extends support for widely used libraries such as PyTorch-Lightning for training, HuggingFace datasets for dataset reading, and Hydra for experiment configuration. Supplementary libraries and GitHub templates for the easy setup of new projects are also provided. By ensuring functionality and versatility, PyTorch-IE provides vital support to the research community engaged in Information Extraction.