CUT: Controllable Unsupervised Text Simplification

12/03/2020
by   Oleg Kariuk, et al.
0

In this paper, we focus on the challenge of learning controllable text simplifications in unsupervised settings. While this problem has been previously discussed for supervised learning algorithms, the literature on the analogies in unsupervised methods is scarse. We propose two unsupervised mechanisms for controlling the output complexity of the generated texts, namely, back translation with control tokens (a learning-based approach) and simplicity-aware beam search (decoding-based approach). We show that by nudging a back-translation algorithm to understand the relative simplicity of a text in comparison to its noisy translation, the algorithm self-supervises itself to produce the output of the desired complexity. This approach achieves competitive performance on well-established benchmarks: SARI score of 46.88 and FKGL of 3.65

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/26/2022

SentBS: Sentence-level Beam Search for Controllable Summarization

A wide range of control perspectives have been explored in controllable ...
research
05/24/2023

How To Control Text Simplification? An Empirical Study of Control Tokens for Meaning Preserving Controlled Simplification

Text simplification rewrites text to be more readable for a specific aud...
research
04/27/2022

Self-Supervised Text Erasing with Controllable Image Synthesis

Recent efforts on scene text erasing have shown promising results. Howev...
research
07/06/2017

Single-Queue Decoding for Neural Machine Translation

Neural machine translation models rely on the beam search algorithm for ...
research
06/17/2020

Iterative Edit-Based Unsupervised Sentence Simplification

We present a novel iterative, edit-based approach to unsupervised senten...
research
07/09/2019

NTT's Machine Translation Systems for WMT19 Robustness Task

This paper describes NTT's submission to the WMT19 robustness task. This...

Please sign up or login with your details

Forgot password? Click here to reset