Neural Relation Extraction Within and Across Sentence Boundaries

TL;DR

This paper introduces iDepNN, a neural network architecture that models dependency paths to improve relation extraction across sentence boundaries, achieving state-of-the-art results in news and medical datasets.

Contribution

The paper presents a novel neural network architecture, iDepNN, specifically designed for inter-sentential relation extraction, outperforming existing methods and providing new cross-sentence annotations.

Findings

iDepNN outperforms SVM and neural baselines in relation extraction.

Achieves state-of-the-art performance on MUC6 and BioNLP datasets.

Improves F1 score by 5.2% over the winning team in BioNLP shared task.

Abstract

Past work in relation extraction mostly focuses on binary relation between entity pairs within single sentence. Recently, the NLP community has gained interest in relation extraction in entity pairs spanning multiple sentences. In this paper, we propose a novel architecture for this task: inter-sentential dependency-based neural networks (iDepNN). iDepNN models the shortest and augmented dependency paths via recurrent and recursive neural networks to extract relationships within (intra-) and across (inter-) sentence boundaries. Compared to SVM and neural network baselines, iDepNN is more robust to false positives in relationships spanning sentences. We evaluate our models on four datasets from newswire (MUC6) and medical (BioNLP shared task) domains that achieve state-of-the-art performance and show a better balance in precision and recall for inter-sentential relationships. We perform better than 11 teams participating in the BioNLP shared task 2016 and achieve a gain of 5.2% (0.587 vs 0.558) in F1 over the winning team. We also release the crosssentence annotations for MUC6.