Mandya, Angrosh, Bollegala, Danushka, Coenen, Frans and Atkinson, Katie
(2018)
Combining Long Short Term Memory and Convolutional Neural Network for
Cross-Sentence n-ary Relation Extraction.
CoRR, abs/18.
Text
mandya-combining long short term memory and convolutional neural network for cross-sentence n-ary relation extractiona.pdf - Submitted version Download (342kB) | Preview |
|
Text
1811.00845v1.pdf - Submitted version Download (374kB) | Preview |
Abstract
We propose in this paper a combined model of Long Short Term Memory and Convolutional Neural Networks (LSTM-CNN) 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 dataset 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 LSTM-CNN model outperforms the current state-of-the-art methods on cross-sentence n-ary relation extraction.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | cs.IR, cs.IR, cs.CL |
Depositing User: | Symplectic Admin |
Date Deposited: | 27 Feb 2020 10:26 |
Last Modified: | 19 Jan 2023 00:43 |
Related URLs: | |
URI: | https://livrepository.liverpool.ac.uk/id/eprint/3042462 |