# An Augmented Transformer Architecture for Natural Language Generation Tasks

arXiv: https://arxiv.org/abs/1910.13634 · HTML: https://mlsanity.com/paper/1910.13634/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2019.

## Built on by (most cited first, 3 of 3)

- [Position Information in Transformers: An Overview](https://mlsanity.com/paper/2102.11090/) (2021)
- [Base of RoPE Bounds Context Length](https://mlsanity.com/paper/2405.14591/) (2024)
- [Improving English to Sinhala Neural Machine Translation using Part-of-Speech Tag](https://mlsanity.com/paper/2202.08882/) (2022)

## Abstract (arXiv)

The Transformer based neural networks have been showing significant advantages on most evaluations of various natural language processing and other sequence-to-sequence tasks due to its inherent architecture based superiorities. Although the main architecture of the Transformer has been continuously being explored, little attention was paid to the positional encoding module. In this paper, we enhance the sinusoidal positional encoding algorithm by maximizing the variances between encoded consecutive positions to obtain additional promotion. Furthermore, we propose an augmented Transformer architecture encoded with additional linguistic knowledge, such as the Part-of-Speech (POS) tagging, to boost the performance on some natural language generation tasks, e.g., the automatic translation and summarization tasks. Experiments show that the proposed architecture attains constantly superior results compared to the vanilla Transformer.