Technische Universität Darmstadt(达姆施塔特工业大学);DeepMind(深度思维);Insight Centre, NUI Galway(爱尔兰国立大学戈尔韦分校洞察中心);Aylien Ltd.(Aylien有限公司);New York University(纽约大学)
Jonas Pfeiffer, Aishwarya Kamath, Iryna Gurevych, Sebastian Ruder
Recent research towards understanding neural networks probes models in a top-down manner, but is only able to identify model tendencies that are known a priori. We propose Susceptibility Identification through Fine-Tuning (SIFT), a novel abstractive method that uncovers a model's preferences without imposing any prior. By fine-tuning an autoencoder with the gradients from a fixed classifier, we are able to extract propensities that characterize different kinds of classifiers in a bottom-up manner. We further leverage the SIFT architecture to rephrase sentences in order to predict the opposing class of the ground truth label, uncovering potential artifacts encoded in the fixed classification model. We evaluate our method on three diverse tasks with four different models. We contrast the propensities of the models as well as reproduce artifacts reported in the literature.
Read What You Hear: Reference-Free Hypotheses Evaluation with Acoustic Discrepancy
X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, China(X-LANCE实验室、计算机科学学院、上海交通大学、中国);MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, China(人工智能MOE重点实验室、江苏省语言计算重点实验室、中国)
What is not where: the challenge of integrating spatial representations into deep learning architectures
ADAPT Centre for Digital Content Technology(ADAPT数字内容技术中心);Dublin Institute of Technology(都柏林理工学院);CLASP and FLOV(CLASP与FLOV);University of Gotenburg(哥德堡大学)