Modern Methods for Text Generation

09/10/2020 ∙ by Dimas Munoz Montesinos, et al. ∙ 0

Synthetic text generation is challenging and has limited success. Recently, a new architecture, called Transformers, allow machine learning models to understand better sequential data, such as translation or summarization. BERT and GPT-2, using Transformers in their cores, have shown a great performance in tasks such as text classification, translation and NLI tasks. In this article, we analyse both algorithms and compare their output quality in text generation tasks.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 7

page 8

Code Repositories

transformers

Bunch of experiments with Transformers, BERT and GPT-2. Experiments include question-answering and conditional text generation.


view repo
This week in AI

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