Controllable Text Generation with Focused Variation

09/25/2020
by   Lei Shu, et al.
0

This work introduces Focused-Variation Network (FVN), a novel model to control language generation. The main problems in previous controlled language generation models range from the difficulty of generating text according to the given attributes, to the lack of diversity of the generated texts. FVN addresses these issues by learning disjoint discrete latent spaces for each attribute inside codebooks, which allows for both controllability and diversity, while at the same time generating fluent text. We evaluate FVN on two text generation datasets with annotated content and style, and show state-of-the-art performance as assessed by automatic and human evaluations.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

05/07/2021

On-the-Fly Controlled Text Generation with Experts and Anti-Experts

Despite recent advances in natural language generation, it remains chall...
01/22/2022

A Causal Lens for Controllable Text Generation

Controllable text generation concerns two fundamental tasks of wide appl...
10/14/2021

MReD: A Meta-Review Dataset for Controllable Text Generation

When directly using existing text generation datasets for controllable g...
11/08/2020

Adapting a Language Model for Controlled Affective Text Generation

Human use language not just to convey information but also to express th...
05/28/2019

Unsupervised Controllable Text Generation with Global Variation Discovery and Disentanglement

Existing controllable text generation systems rely on annotated attribut...
05/05/2020

Russian Natural Language Generation: Creation of a Language Modelling Dataset and Evaluation with Modern Neural Architectures

Generating coherent, grammatically correct, and meaningful text is very ...
07/01/2017

SAM: Semantic Attribute Modulation for Language Modeling and Style Variation

This paper presents a Semantic Attribute Modulation (SAM) for language m...
This week in AI

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