Figure 2 - uploaded by Zhenghao Wu
Content may be subject to copyright.
Examining hyperparameter ℵ on the AEG dataset. ROUGE-L F1 scores and Length Variance V ar of different models under different ℵ are shown (ℵ = 2, 10, 50, 250).

Examining hyperparameter ℵ on the AEG dataset. ROUGE-L F1 scores and Length Variance V ar of different models under different ℵ are shown (ℵ = 2, 10, 50, 250).

Contexts in source publication

Context 1
... suggests that the adding of LenAtten can boost language model performance. Figure 2 shows the length controllability becomes better as the increase of ℵ, with no harm to the ROUGE-L scores. ...
Context 2
... suggests that the adding of LenAtten can boost language model performance. Figure 2 shows the length controllability becomes better as the increase of ℵ, with no harm to the ROUGE-L scores. ...

Similar publications

Article
Full-text available
Understanding how two datasets differ can help us determine whether one dataset under-represents certain sub-populations, and provides insights into how well models will generalize across datasets. Representative points selected by a maximum mean discrepancy (MMD) coreset can provide interpretable summaries of a single dataset, but are not easily c...
Article
Full-text available
More than 30 inflationary models are confronted with the recently improved limit on the tensor-to-scalar ratio presented by the Planck team. I show that a few more models are falsified due to this sharper restriction. Additionally, I discuss possible consequences of CMB-S4 observations for these inflationary models. The results are summarized in a...
Chapter
Full-text available
This chapter summarizes and concludes the contribution of this thesis in Section 6.1 and Section 6.2, respectively. Section 6.3 provides an overview of future work projects.