Learning to Extract Structured Entities Using Language Models

TL;DR

This paper introduces a new entity-centric approach to information extraction using language models, proposing a novel metric and a multistage model that outperform baselines in structured entity extraction tasks.

Contribution

It presents the Structured Entity Extraction framework, the AESOP metric, and the MuSEE model, advancing the effectiveness and evaluation of entity extraction methods.

Findings

MuSEE outperforms baseline models in accuracy.

AESOP provides more nuanced performance assessment.

Entity-centric reformulation offers better insights than triplet-centric methods.

Abstract

Recent advances in machine learning have significantly impacted the field of information extraction, with Language Models (LMs) playing a pivotal role in extracting structured information from unstructured text. Prior works typically represent information extraction as triplet-centric and use classical metrics such as precision and recall for evaluation. We reformulate the task to be entity-centric, enabling the use of diverse metrics that can provide more insights from various perspectives. We contribute to the field by introducing Structured Entity Extraction and proposing the Approximate Entity Set OverlaP (AESOP) metric, designed to appropriately assess model performance. Later, we introduce a new Multistage Structured Entity Extraction (MuSEE) model that harnesses the power of LMs for enhanced effectiveness and efficiency by decomposing the extraction task into multiple stages. Quantitative and human side-by-side evaluations confirm that our model outperforms baselines, offering promising directions for future advancements in structured entity extraction. Our source code and datasets are available at https://github.com/microsoft/Structured-Entity-Extraction.