Large-scale Exploration of Neural Relation Classification Architectures

Le, Hoang Quynh and Can, Duy Cat and Vu, Tien Sinh and Dang, Thanh Hai and Pilehvar, Mohammad Taher and Collier, Nigel (2018) Large-scale Exploration of Neural Relation Classification Architectures. In: Conference on Empirical Methods in Natural Language Processing (EMNLP 2018), October 31 - November 4 2018, Brussels, Belgium.

PDF Download (651kB)

Abstract

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.

Item Type:	Conference or Workshop Item (Paper)
Subjects:	Information Technology (IT)
Divisions:	Faculty of Information Technology (FIT)
Depositing User:	Duy-Cat Can
Date Deposited:	19 Nov 2018 11:09
Last Modified:	19 Nov 2018 11:09
URI:	http://eprints.uet.vnu.edu.vn/eprints/id/eprint/3171

Actions (login required)

View Item