Hung-Yi Lee, Chun-Hsing Lin, Siang-Ruei Wu, Yun-Nung Chen
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Score function-based natural language generation (NLG) approaches such as RE-INFORCE, in general, suffer from low sample efficiency and training instability problems. This is mainly due to the non-differentiable nature of the discrete space sampling and thus these methods have to treat the discriminator as a black box and ignore the gradient information. To improve the sample efficiency and reduce the variance of REINFORCE, we propose a novel approach, TaylorGAN, which augments the gradient estimation by off-policy update and the first-order Taylor expansion. This approach enables us to train NLG models from scratch with smaller batch size -without maximum likelihood pre-training, and outperforms existing GAN-based methods on multiple metrics of quality and diversity. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2011.13527")
get_code_for_paper("2011.13527")
have("2011.13527")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2011.13527.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2011.13527)
Connect an agent — have() is free.