Towards Transparent and Explainable Attention Models
Indian Institute of Technology Madras（马德拉斯印度理工学院）；Robert Bosch Center for Data Science and Artificial Intelligence, IIT Madras（印度理工学院马德拉斯分校罗伯特·博世数据科学与人工智能中心）；Adobe Research（Adobe研究院）
Recent studies on interpretability of attention distributions have led to notions of faithful and plausible explanations for a model's predictions. Attention distributions can be considered a faithful explanation if a higher attention weight implies a greater impact on the model's prediction. They can be considered a plausible explanation if they provide a human-understandable justification for the model's predictions. In this work, we first explain why current attention mechanisms in LSTM based encoders can neither provide a faithful nor a plausible explanation of the model's predictions. We observe that in LSTM based encoders the hidden representations at different time-steps are very similar to each other (high conicity) and attention weights in these situations do not carry much meaning because even a random permutation of the attention weights does not affect the model's predictions. Based on experiments on a wide variety of tasks and datasets, we observe attention distributions often attribute the model's predictions to unimportant words such as punctuation and fail to offer a plausible explanation for the predictions. To make attention mechanisms more faithful and plausible, we propose a modified LSTM cell with a diversity-driven training objective that ensures that the hidden representations learned at different time steps are diverse. We show that the resulting attention distributions offer more transparency as they (i) provide a more precise importance ranking of the hidden states (ii) are better indicative of words important for the model's predictions (iii) correlate better with gradient-based attribution methods. Human evaluations indicate that the attention distributions learned by our model offer a plausible explanation of the model's predictions. Our code has been made publicly available at https://github.com/akashkm99/Interpretable-Attention
Towards Explainable Evaluation Metrics for Natural Language Generation
Technische Universität Darmstadt（达姆施塔特工业大学）；Imperial College London（伦敦帝国学院）；University of Sheffield（谢菲尔德大学）；Heidelberg Institute for Theoretical Studies（海德堡理论研究所）；Google Research（谷歌研究院）
Hierarchical Label-wise Attention Transformer Model for Explainable ICD Coding
University of New South Wales（新南威尔士大学）；The Australian e-Health Research Centre, CSIRO（澳大利亚联邦科学与工业研究组织澳大利亚电子健康研究中心）；Australian Institute of Health and Welfare（澳大利亚卫生与福利研究所）
Explainable Text-Driven Neural Network for Stock Prediction
Insight Centre for Data Analytics（洞察数据分析中心）；University College Dublin（都柏林大学学院）；Beijing Dublin International College（北京都柏林国际学院）；School of Computer Science（计算机科学学院）
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Lehigh University（理海大学）；University of Georgia（佐治亚大学）；Iowa State University（爱荷华州立大学）；Computational Bioscience Research Center（计算生物科学研究中心）；SDAIA-KAUST Center of Excellence in Data Science and Artificial Intelligence（沙特数据与人工智能局-阿卜杜拉国王科技大学数据科学与人工智能卓越中心）
RECA-PD: A Robust Explainable Cross-Attention Method for Speech-based Parkinson's Disease Classification
Centre for Language Studies, Radboud University, Nijmegen, the Netherlands（语言研究中心，拉德堡德大学，尼迈根，荷兰）；Center of Expertise for Parkinson and Movement Disorders, Radboud University Medical Center, Nijmegen, the Netherlands（帕金森病与运动障碍专家中心，拉德堡德大学医学中心，尼迈根，荷兰）
