Xê-mi-na khoa học
16/10/2018: ThS. Lê Hoàng Quỳnh (ĐH Công nghệ), Large-scale Exploration of Neural Relation Classification Architectures
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.
Speaker: ThS. Lê Hoàng Quỳnh, ĐH Công nghệ
Time: 15:30, Tuesday, October 16, 2018
Venue: E3-707, 144 Xuan Thuy, Cau Giay, Hanoi
Le Hoang Quynh was a researcher at the Data Science and Knowledge Technology Lab at VNUH UET. She was also PhD student under supervised by Prof. Nigel Collier (Cambridge University, UK) and Dr. Dang Thanh Hai (UET VNU). She is currently working on the biomedical text mining field which lies at the intersection of Natural Language Processing and Biomedical science. Her research interests are, among others, named entity recognition, relation extraction and event extraction.