Multidimensional Analysis of Trust in News Articles
Avneet Kaur, Maitree Leekha, et al.
AAAI 2020
Continuous representation of words is a standard component in deep learning-based NLP models. However, representing a large vocabulary requires significant memory, which can cause problems, particularly on resource-constrained platforms. Therefore, in this paper we propose an isotropic iterative quantization (IIQ) approach for compressing embedding vectors into binary ones, leveraging the iterative quantization technique well established for image retrieval, while satisfying the desired isotropic property of PMI based models. Experiments with pre-trained embeddings (i.e., GloVe and HDC) demonstrate a more than thirty-fold compression ratio with comparable and sometimes even improved performance over the original real-valued embedding vectors.
Avneet Kaur, Maitree Leekha, et al.
AAAI 2020
Guy Barash, Onn Shehory, et al.
AAAI 2020
Shaokai Ye, Kaidi Xu, et al.
ICCV 2019
Jie Chen, Lois C. McInnes, et al.
Journal of Scientific Computing