Dirichlet Prior

Existing word similarity measures are not robust to data sparseness since they rely only on the point estimation of words’ context profiles obtained from a limited amount of data. This …...

AbstractAdvances on deep generative models have attracted significant research interest in neural topic modeling. The recently proposed Adversarial-neural Topic Model models topics with an adversarially trained generator network and employs …...

AbstractIn this paper, we seek to improve the faithfulness of TempRel extraction models from two perspectives. The first perspective is to extract genuinely based on contextual description. To achieve this, …...