Large-scale Exploration of Neural Relation Classification Architectures
Large-scale Exploration of Neural Relation Classification Architectures
复制标题
DOI：
10.18653/v1/d18-1250
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Hoang-Quynh Le;Duy-Cat Can;Sinh T. Vu;T. Dang;Mohammad Taher Pilehvar;Nigel Collier
中科院分区：
文献类型：
--
作者：
Hoang-Quynh Le;Duy-Cat Can;Sinh T. Vu;T. Dang;Mohammad Taher Pilehvar;Nigel Collier
使用深度神经网络架构，关系分类任务的实验性能普遍得到改善。已报道研究的一个主要缺点是，单个模型是在非常狭窄的数据集上进行评估的，这引发了有关架构适应性的问题，同时使得方法之间的比较变得困难。在这项工作中，我们对六个具有广泛不同特征的基准数据集进行了神经关系分类架构的系统性大规模分析。我们提出了一种与 CNN 相结合的新颖的多通道 LSTM 模型，该模型利用了当前流行的所有语言和架构特征。我们的“Man for All Seasons”方法在两个数据集上实现了最先进的性能。更重要的是，我们认为该模型使我们能够直接了解神经语言模型在这项任务上面临的持续挑战。
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.