CLApr 26, 2020
Experiments with LVT and FRE for Transformer model
arXiv:2004.12495v1
AI Analysis
This work addresses text summarization for NLP researchers, but it is incremental as it explores known techniques without achieving improvements.
The authors applied Large Vocabulary Trick and Feature-rich encoding to Transformer models for text summarization but found they did not outperform analogous RNN-based sequence-to-sequence models, leading to further experiments to identify factors affecting performance.
In this paper, we experiment with Large Vocabulary Trick and Feature-rich encoding applied to the Transformer model for Text Summarization. We could not achieve better results, than the analogous RNN-based sequence-to-sequence model, so we tried more models to find out, what improves the results and what deteriorates them.