Author(s): Ala Alam Falaki

Originally published on Towards AI.

Training

Is it possible to train a model with transformer architecture to learn generating summaries with different styles?

Figure 1. The multi-decoder architecture scheme. (Image from [1])

While it’s true that deep learning (specifically transformer architecture) keeps pushing the SOTA scores, they have a kind of significant shortcoming. No, I am not talking about their memory usage! We know how to train them, but we do not have any control over what they will learn. For instance, it is a missing feature in Text Summarization models to control the output to set a length or style. Let’s see if we can do anything… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI