English

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

Information Retrieval 2018-11-05 v1 Computation and Language

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.

Keywords

Cite

@article{arxiv.1811.00845,
  title  = {Combining Long Short Term Memory and Convolutional Neural Network for Cross-Sentence n-ary Relation Extraction},
  author = {Angrosh Mandya and Danushka Bollegala and Frans Coenen and Katie Atkinson},
  journal= {arXiv preprint arXiv:1811.00845},
  year   = {2018}
}
R2 v1 2026-06-23T05:02:03.069Z