Explanation-based model debugging aims to resolve spurious biases by showing human users explanations of model behavior, asking users to give feedback on the behavior, then using the feedback to update the model.
As the refiner, we train a diffusion-based generative model by utilizing a dataset consisting of clean speech only.
1 code implementation • 16 May 2022 • Yuhta Takida, Takashi Shibuya, WeiHsiang Liao, Chieh-Hsin Lai, Junki Ohmura, Toshimitsu Uesaka, Naoki Murata, Shusuke Takahashi, Toshiyuki Kumakura, Yuki Mitsufuji
In this paper, we propose a new training scheme that extends the standard VAE via novel stochastic dequantization and quantization, called stochastically quantized variational autoencoder (SQ-VAE).
We also find that good demonstration can save many labeled examples and consistency in demonstration contributes to better performance.
When an entity name contains other names within it, the identification of all combinations of names can become difficult and expensive.
Ranked #2 on Nested Mention Recognition on ACE 2005