TY  - CONF
ID  - SisLab3171
UR  - http://www.aclweb.org/anthology/D18-1250
A1  - Le, Hoang Quynh
A1  - Can, Duy Cat
A1  - Vu, Tien Sinh
A1  - Dang, Thanh Hai
A1  - Pilehvar, Mohammad Taher
A1  - Collier, Nigel
Y1  - 2018///
N2  - Experimental performance on the task of relation classification has generally improved using deep neural network architectures. One major drawback of reported studies is that individual models have been evaluated on a very narrow range of datasets, raising questions about the adaptability of the architectures, while making comparisons between approaches difficult. In this work, we present a systematic large-scale analysis of neural relation classification architectures on six benchmark datasets with widely varying characteristics. We propose a novel multi-channel LSTM model combined with a CNN that takes advantage of all currently popular linguistic and architectural features. Our ?Man for All Seasons? approach achieves state-of-the-art performance on two datasets. More importantly, in our view, the model allowed us to obtain direct insights into the continued challenges faced by neural language models on this task. Example data and source code are available at: https://github. com/aidantee/MASS.
TI  - Large-scale Exploration of Neural Relation Classification Architectures
SP  - 2266
M2  - Brussels, Belgium
AV  - public
EP  - 2277
T2  - Conference on Empirical Methods in Natural Language Processing (EMNLP 2018)
ER  -