# PyTorch-IE: Fast and Reproducible Prototyping for Information Extraction

arXiv: https://arxiv.org/abs/2406.00007 · HTML: https://mlsanity.com/paper/2406.00007/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 16 May 2024.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Datasets: A Community Library for Natural Language Processing](https://mlsanity.com/paper/2109.02846/) (2021)
- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [A Unified Generative Framework for Various NER Subtasks](https://mlsanity.com/paper/2106.01223/) (2021)
- [Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction](https://mlsanity.com/paper/2106.09232/) (2021)
- [ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning](https://mlsanity.com/paper/2012.15022/) (2020)
- [Joint Entity and Relation Extraction with Set Prediction Networks](https://mlsanity.com/paper/2011.01675/) (2020)
- [HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extraction](https://mlsanity.com/paper/2106.15838/) (2021)
- [A Corpus Study and Annotation Schema for Named Entity Recognition and Relation Extraction of Business Products](https://mlsanity.com/paper/2004.03287/) (2020)

## Abstract (arXiv)

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.