An Augmented Transformer Architecture for Natural Language Generation Tasks

10/30/2019 ∙ by Hailiang Li, et al. ∙ 0

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 6

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.