Log In Sign Up

A Neural Edge-Editing Approach for Document-Level Relation Graph Extraction

by   Kohei Makino, et al.

In this paper, we propose a novel edge-editing approach to extract relation information from a document. We treat the relations in a document as a relation graph among entities in this approach. The relation graph is iteratively constructed by editing edges of an initial graph, which might be a graph extracted by another system or an empty graph. The way to edit edges is to classify them in a close-first manner using the document and temporally-constructed graph information; each edge is represented with a document context information by a pretrained transformer model and a graph context information by a graph convolutional neural network model. We evaluate our approach on the task to extract material synthesis procedures from materials science texts. The experimental results show the effectiveness of our approach in editing the graphs initialized by our in-house rule-based system and empty graphs.


page 1

page 2

page 3

page 4


Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs

Document-level relation extraction is a complex human process that requi...

Graph Refinement for Coreference Resolution

The state-of-the-art models for coreference resolution are based on inde...

ConstGCN: Constrained Transmission-based Graph Convolutional Networks for Document-level Relation Extraction

Document-level relation extraction with graph neural networks faces a fu...

A Polynomial Kernel for Diamond-Free Editing

An H-free editing problem asks whether we can edit at most k edges to ma...

Responsive Matrix Cells: A Focus+Context Approach for Exploring and Editing Multivariate Graphs

Matrix visualizations are a useful tool to provide a general overview of...

DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases

Keyphrase extraction from documents is useful to a variety of applicatio...

Orthogonal Edge Routing for the EditLens

The EditLens is an interactive lens technique that supports the editing ...

Code Repositories


The source code for "A Neural Edge-Editing Approach for Document-Level Relation Graph Extraction" in Findings of ACL-IJCNLP 2021

view repo