Search Results for author:
Found 3 papers, 0 papers with code
HI-CMLM: Improve CMLM with Hybrid Decoder Input
Mask-predict CMLM (Ghazvininejad et al., 2019) has achieved stunning performance among non-autoregressive NMT models, but we find that the mechanism of predicting all of the target words only depending on the hidden state of [MASK] is not effective and efficient in initial iterations of refinement, resulting in ungrammatical repetitions and slow convergence.
How Length Prediction Influence the Performance of Non-Autoregressive Translation?
Length prediction is a special task in a series of NAT models where target length has to be determined before generation.
Improvement of K Mean Clustering Algorithm Based on Density
The purpose of this paper is to improve the traditional K-means algorithm.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
