Zero-Shot Style Transfer in Text Using Recurrent Neural Networks

11/13/2017
by   Keith Carlson, et al.
0

Zero-shot translation is the task of translating between a language pair where no aligned data for the pair is provided during training. In this work we employ a model that creates paraphrases which are written in the style of another existing text. Since we provide the model with no paired examples from the source style to the target style during training, we call this task zero-shot style transfer. Herein, we identify a high-quality source of aligned, stylistically distinct text in Bible versions and use this data to train an encoder/decoder recurrent neural model. We also train a statistical machine translation system, Moses, for comparison. We find that the neural network outperforms Moses on the established BLEU and PINC metrics for evaluating paraphrase quality. This technique can be widely applied due to the broad definition of style which is used. For example, tasks like text simplification can easily be viewed as style transfer. The corpus itself is highly parallel with 33 distinct Bible Versions used, and human-aligned due to the presence of chapter and verse numbers within the text. This makes the data a rich source of study for other natural language tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/08/2021

A Recipe For Arbitrary Text Style Transfer with Large Language Models

In this paper, we leverage large language models (LMs) to perform zero-s...
research
05/28/2023

StyleS2ST: Zero-shot Style Transfer for Direct Speech-to-speech Translation

Direct speech-to-speech translation (S2ST) has gradually become popular ...
research
08/01/2018

Monolingual and Cross-lingual Zero-shot Style Transfer

We introduce the task of zero-shot style transfer between different lang...
research
03/27/2019

Grammatical Error Correction and Style Transfer via Zero-shot Monolingual Translation

Both grammatical error correction and text style transfer can be viewed ...
research
06/02/2023

Text Style Transfer Back-Translation

Back Translation (BT) is widely used in the field of machine translation...
research
09/19/2021

Preventing Author Profiling through Zero-Shot Multilingual Back-Translation

Documents as short as a single sentence may inadvertently reveal sensiti...
research
04/06/2018

Mix and match networks: encoder-decoder alignment for zero-pair image translation

We address the problem of image translation between domains or modalitie...

Please sign up or login with your details

Forgot password? Click here to reset