Combining Long Short Term Memory and Convolutional Neural Network for Cross-Sentence n-ary Relation Extraction
- Keywords: n-ary relation extraction, information extraction
- Abstract: A combined Long Short Term Memory and Convolutional Neural Networks (lstm_cnn+wf+pf) that exploits word embeddings and positional embeddings is proposed for cross-sentence n-ary relation extraction. The proposed model brings together the properties of lstms and cnns, to simultaneously exploit long-range sequential information and capture the most informative features, essential for cross-sentence n-ary relation extraction. The lstm_cnn+wf+pf model was evaluated using standard datasets for cross-sentence n-ary relation extraction, where the model significantly outperforms baseline cnn and lstm model and a combined cnn_lstm model. The paper also shows that the lstm_cnn model outperforms the current state-of-the-art methods on cross-sentence n-ary relation extraction.
- Archival status: Non-Archival
- Subject areas: Information Extraction, Applications: Biomedicine
0 Replies