Search Results for author:
Found 3 papers, 0 papers with code
OUMG: Objective and Universal Metric for Text Generation with Guiding Ability
We train a discriminator to distinguish between human-generated and machine-generated text, which is used to score the sentences generated by the model.
Multi-scale fusion self attention mechanism
Based on the traditional attention mechanism, multi-scale fusion self attention extracts phrase information at different scales by setting convolution kernels at different levels, and calculates the corresponding attention matrix at different scales, so that the model can better extract phrase level information.
GSD: Generalized Stochastic Decoding
Correctly, we propose a generalized decoding framework that can be used to describe and connect existing popular decoding algorithms.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
