Document-level Entity-based Extraction as Template Generation

TL;DR

This paper introduces a generative template-based approach with a novel copy mechanism for document-level entity extraction, significantly improving accuracy over previous extractive models by capturing long-term dependencies and label semantics.

Contribution

It proposes a new generative framework and a cross-attention guided copy mechanism for document-level entity extraction, achieving state-of-the-art results.

Findings

State-of-the-art F1 scores on REE, binary RE, and 4-ary RE datasets.

Effective modeling of long-term entity dependencies.

Enhanced extraction accuracy with the TopK Copy mechanism.

Abstract

Document-level entity-based extraction (EE), aiming at extracting entity-centric information such as entity roles and entity relations, is key to automatic knowledge acquisition from text corpora for various domains. Most document-level EE systems build extractive models, which struggle to model long-term dependencies among entities at the document level. To address this issue, we propose a generative framework for two document-level EE tasks: role-filler entity extraction (REE) and relation extraction (RE). We first formulate them as a template generation problem, allowing models to efficiently capture cross-entity dependencies, exploit label semantics, and avoid the exponential computation complexity of identifying N-ary relations. A novel cross-attention guided copy mechanism, TopK Copy, is incorporated into a pre-trained sequence-to-sequence model to enhance the capabilities of identifying key information in the input document. Experiments done on the MUC-4 and SciREX dataset show new state-of-the-art results on REE (+3.26%), binary RE (+4.8%), and 4-ary RE (+2.7%) in F1 score.