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

We propose in this paper a combined model of Long Short Term Memory and\nConvolutional Neural Networks (LSTM-CNN) that exploits word embeddings and\npositional embeddings for cross-sentence n-ary relation extraction. The\nproposed model brings together the properties of both LSTMs and CNNs, to\nsimultaneously exploit long-range sequential information and capture most\ninformative features, essential for cross-sentence n-ary relation extraction.\nThe LSTM-CNN model is evaluated on standard dataset on cross-sentence n-ary\nrelation extraction, where it significantly outperforms baselines such as CNNs,\nLSTMs and also a combined CNN-LSTM model. The paper also shows that the\nLSTM-CNN model outperforms the current state-of-the-art methods on\ncross-sentence n-ary relation extraction.\n