Using LSTM Encoder-Decoder for Rhetorical Structure Prediction
Gustavo Bennemann de Moura, Valéria Delisandra Feltrim · 2018
The importance of identifying rhetorical categories in texts has been widely acknowledged in the literature, since information regarding text organization or structure can be applied in a variety of scenarios, including genre-specific writing support and evaluation, both manually and automatically. In this paper we present a Long Short-Term Memory (LSTM) encoder-decoder classifier for scientific abstracts. As a large corpus of annotated abstracts was required to train our classifier, we built a corpus using abstracts extracted from PUBMED/MEDLINE. Using the proposed classifier we achieved approximately 3% improvement in per-abstract accuracy over the baselines and 1% improvement for both per-sentence accuracy and f1-score.