Evaluating prose style transfer with the Bible

@article{Carlson2018EvaluatingPS,
  title={Evaluating prose style transfer with the Bible},
  author={Keith Carlson and Allen B. Riddell and Daniel N. Rockmore},
  journal={Royal Society Open Science},
  year={2018},
  volume={5}
}
In the prose style transfer task a system, provided with text input and a target prose style, produces output which preserves the meaning of the input text but alters the style. These systems require parallel data for evaluation of results and usually make use of parallel data for training. Currently, there are few publicly available corpora for this task. In this work, we identify a high-quality source of aligned, stylistically distinct text in different versions of the Bible. We provide a… Expand

Figures, Tables, and Topics from this paper

An Empirical Study on Multi-Task Learning for Text Style Transfer and Paraphrase Generation
TLDR
An efficient method for neutral-to-style transformation using the transformer framework is presented and a synthetic measure for the automatic evaluation of style transfer models is proposed. Expand
Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites
TLDR
This paper shows that standard assessment methodology for style transfer has several significant problems, and suggests taking BLEU between input and human-written reformulations into consideration for benchmarks, and proposes three new architectures that outperform state of the art in terms of this metric. Expand
Style Transfer for Texts: to Err is Human, but Error Margins Matter
TLDR
This paper shows that standard assessment methodology for style transfer has several significant problems, and suggests taking BLEU between input and human-written reformulations into consideration for benchmarks, and proposes three new architectures that outperform state of the art in terms of this metric. Expand
TextSETTR: Label-Free Text Style Extraction and Tunable Targeted Restyling
TLDR
This work shows that T5 (Raffel et al., 2020), a strong pretrained text-to-text model, can be adapted to extract a style vector from arbitrary text and use this vector to condition the decoder to perform style transfer, and recast transfers as "targeted restyling" vector operations that adjust specific attributes of the input text while preserving others. Expand
Improving Neural Text Style Transfer by Introducing Loss Function Sequentiality
TLDR
This paper shows that the sequential introduction of different loss functions into the learning process can boost the performance of a standard model and evidence that combining different style classifiers that either focus on global or local textual information improves sentence generation. Expand
An Evaluation of Disentangled Representation Learning for Texts
TLDR
A systematic investigation of previously proposed loss functions for such models are conducted and they are evaluated on a highly-structured and synthetic natural language dataset that is well-suited for the task of disentangled representation learning, as well as two other parallel style transfer datasets. Expand
Generative Text Style Transfer for Improved Language Sophistication
Recent advances in Natural Language Processing (NLP) have heightened interest in generative text models and style transfer tasks. While most research has focused on binary sentiment transfer, someExpand
HELFI: a Hebrew-Greek-Finnish Parallel Bible Corpus with Cross-Lingual Morpheme Alignment
TLDR
A nontrivial editorial process starting from the creation of the original one-purpose database and ending with its reconstruction using only freely available text editions and annotations produced an openly available dataset that contains the source texts and their translations. Expand
Marvin: Stylistic Language Editor Final Report
Using contemporary natural language processing (NLP) methods, we have created an AI powered tool for writing called “Marvin”. Our project specifically aims to understand how to generate and editExpand
Deep Learning for Text Attribute Transfer: A Survey.
TLDR
This article collects all related academic works since the first appearance in 2017, and reveals that existing methods are indeed based on a combination of several loss functions with each of which serving a certain goal. Expand
...
1
2
...

References

SHOWING 1-10 OF 80 REFERENCES
Paraphrasing for Style
TLDR
This work shows that even with a relatively small amount of parallel training data, it is possible to learn paraphrase models which capture stylistic phenomena, and these models outperform baselines based on dictionaries and out-of-domain parallel text. Expand
Dear Sir or Madam, May I Introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer
TLDR
This work creates the largest corpus for a particular stylistic transfer (formality) and shows that techniques from the machine translation community can serve as strong baselines for future work. Expand
Style Transfer from Non-Parallel Text by Cross-Alignment
TLDR
This paper proposes a method that leverages refined alignment of latent representations to perform style transfer on the basis of non-parallel text, and demonstrates the effectiveness of this cross-alignment method on three tasks: sentiment modification, decipherment of word substitution ciphers, and recovery of word order. Expand
Stylistic Transfer in Natural Language Generation Systems Using Recurrent Neural Networks
TLDR
This work plans to investigate neural network approaches to NLG to automatically learn and incorporate stylistic features in the process of language generation and identifies several evaluation criteria, and proposes manual and automatic evaluation approaches. Expand
Sentence Simplification by Monolingual Machine Translation
TLDR
By relatively careful phrase-based paraphrasing this model achieves similar simplification results to state-of-the-art systems, while generating better formed output, and argues that text readability metrics such as the Flesch-Kincaid grade level should be used with caution when evaluating the output of simplification systems. Expand
Shakespearizing Modern Language Using Copy-Enriched Sequence-to-Sequence Models
TLDR
This paper explores automated methods to transform text from modern English to Shakespearean English using an end to end trainable neural model with pointers to enable copy action and pre-train embeddings of words. Expand
Unsupervised Neural Machine Translation
TLDR
This work proposes a novel method to train an NMT system in a completely unsupervised manner, relying on nothing but monolingual corpora, and consists of a slightly modified attentional encoder-decoder model that can be trained on monolingUAL corpora alone using a combination of denoising and backtranslation. Expand
Style Transfer in Text: Exploration and Evaluation
TLDR
Two models are explored to learn style transfer with non-parallel data to learn separate content representations and style representations using adversarial networks, and a novel evaluation metrics which measure two aspects of style transfer: transfer strength and content preservation. Expand
Building a Monolingual Parallel Corpus for Text Simplification Using Sentence Similarity Based on Alignment between Word Embeddings
TLDR
This work proposes an unsupervised method that automatically builds the monolingual parallel corpus for text simplification using sentence similarity based on word embeddings using a many-to-one method. Expand
Unsupervised Statistical Machine Translation
TLDR
This paper proposes an alternative approach based on phrase-based Statistical Machine Translation (SMT) that significantly closes the gap with supervised systems, and profits from the modular architecture of SMT. Expand
...
1
2
3
4
5
...