Experiment Segmentation in Scientific Discourse as Clause-level Structured Prediction using Recurrent Neural Networks

TL;DR

This paper introduces a deep learning approach using RNNs with attention mechanisms to identify and segment clauses in scientific experiment narratives, aiding information extraction from scientific texts.

Contribution

It presents a novel RNN-based model with a specialized attention mechanism for clause-level segmentation in scientific discourse, improving upon previous methods.

Findings

The proposed model outperforms baseline LSTM and CRF models.

Attention mechanism enhances clause representation quality.

Potential applications in scientific information extraction.

Abstract

We propose a deep learning model for identifying structure within experiment narratives in scientific literature. We take a sequence labeling approach to this problem, and label clauses within experiment narratives to identify the different parts of the experiment. Our dataset consists of paragraphs taken from open access PubMed papers labeled with rhetorical information as a result of our pilot annotation. Our model is a Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM) cells that labels clauses. The clause representations are computed by combining word representations using a novel attention mechanism that involves a separate RNN. We compare this model against LSTMs where the input layer has simple or no attention and a feature rich CRF model. Furthermore, we describe how our work could be useful for information extraction from scientific literature.