Combining Long Short Term Memory and Convolutional Neural Network for Cross-Sentence n-ary Relation Extraction

Angrosh Mandya, Danushka Bollegala, Frans Coenen, Katie Atkinson

Archival Status: Archival

Subject Areas: Information Extraction, Applications: Biomedicine

Keywords: n-ary relation extraction, information extraction

Abstract: We propose in this paper a combined model of Long Short Term Memory and Convolutional Neural Networks (LSTM_CNN) model that exploits word embeddings and positional embeddings for cross-sentence n-ary relation extraction. The proposed model brings together the properties of both LSTMs and CNNs, to simultaneously exploit long-range sequential information and capture most informative features, essential for cross-sentence n-ary relation extraction. The LSTM_CNN model is evaluated on standard datasets on cross-sentence n-ary relation extraction, where it significantly outperforms baselines such as CNNs, LSTMs and also a combined CNN_LSTM model. The paper also shows that the proposed LSTM_CNN model outperforms the current state-of-the-art methods on cross-sentence n-ary relation extraction.