# Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Network

## TL;DR

This paper introduces a novel document-level graph convolutional neural network for inter-sentence relation extraction, effectively capturing complex dependencies to improve relation prediction across sentences.

## Contribution

It proposes a graph-based neural model that leverages various inter- and intra-sentence dependencies for enhanced relation extraction, utilizing multi-instance learning with bi-affine scoring.

## Key findings

- Achieves comparable performance to state-of-the-art models on biochemistry datasets.
- All types of dependencies in the graph contribute effectively to relation extraction.
- The model effectively captures local and non-local dependencies in documents.

## Abstract

Inter-sentence relation extraction deals with a number of complex semantic relationships in documents, which require local, non-local, syntactic and semantic dependencies. Existing methods do not fully exploit such dependencies. We present a novel inter-sentence relation extraction model that builds a labelled edge graph convolutional neural network model on a document-level graph. The graph is constructed using various inter- and intra-sentence dependencies to capture local and non-local dependency information. In order to predict the relation of an entity pair, we utilise multi-instance learning with bi-affine pairwise scoring. Experimental results show that our model achieves comparable performance to the state-of-the-art neural models on two biochemistry datasets. Our analysis shows that all the types in the graph are effective for inter-sentence relation extraction.