scholarly journals Mask Transformer: Unpaired Text Style Transfer Based on Masked Language

2020 ◽  
Vol 10 (18) ◽  
pp. 6196
Author(s):  
Chunhua Wu ◽  
Xiaolong Chen ◽  
Xingbiao Li
Keyword(s):  
Target Sentence ◽  
Explicit Representation ◽  
Experimental Results ◽  
Current Work ◽  
Semantic Meaning ◽  
Style Transfer ◽  
Original Sentence ◽  
Generation Structure ◽  
Content Preservation ◽  
Transfer Accuracy

Currently, most text style transfer methods encode the text into a style-independent latent representation and decode it into new sentences with the target style. Due to the limitation of the latent representation, previous works can hardly get satisfactory target style sentence especially in terms of semantic remaining of the original sentence. We propose a “Mask and Generation” structure, which can obtain an explicit representation of the content of original sentence and generate the target sentence with a transformer. This explicit representation is a masked text that masks the words with the strong style attribute in the sentence. Therefore, it can preserve most of the semantic meaning of the original sentence. In addition, as it is the input of the generator, it also simplified this process compared to the current work who generate the target sentence from scratch. As the explicit representation is readable and the model has better interpretability, we can clearly know which words changed and why the words changed. We evaluate our model on two review datasets with quantitative, qualitative, and human evaluations. The experimental results show that our model generally outperform other methods in terms of transfer accuracy and content preservation.

scholarly journals Text Style Transfer via Learning Style Instance Supported Latent Space

2020 ◽  
Author(s):  
Xiaoyuan Yi ◽  
Zhenghao Liu ◽  
Wenhao Li ◽  
Maosong Sun
Keyword(s):  
Recent Work ◽  
Learning Style ◽  
Latent Variables ◽  
Paired Data ◽  
Style Transfer ◽  
Parallel Corpora ◽  
Latent Space ◽  
Content Preservation ◽  
Transfer Tasks ◽  
Transfer Accuracy

Text style transfer pursues altering the style of a sentence while remaining its main content unchanged. Due to the lack of parallel corpora, most recent work focuses on unsupervised methods and has achieved noticeable progress. Nonetheless, the intractability of completely disentangling content from style for text leads to a contradiction of content preservation and style transfer accuracy. To address this problem, we propose a style instance supported method, StyIns. Instead of representing styles with embeddings or latent variables learned from single sentences, our model leverages the generative flow technique to extract underlying stylistic properties from multiple instances of each style, which form a more discriminative and expressive latent style space. By combining such a space with the attention-based structure, our model can better maintain the content and simultaneously achieve high transfer accuracy. Furthermore, the proposed method can be flexibly extended to semi-supervised learning so as to utilize available limited paired data. Experiments on three transfer tasks, sentiment modification, formality rephrasing, and poeticness generation, show that StyIns obtains a better balance between content and style, outperforming several recent baselines.

scholarly journals Paraphrase Diversification Using Counterfactual Debiasing

2019 ◽  
Vol 33 ◽  
pp. 6883-6891 ◽  
Author(s):  
Sunghyun Park ◽  
Seung-won Hwang ◽  
Fuxiang Chen ◽  
Jaegul Choo ◽  
Jung-Woo Ha ◽  
...  
Keyword(s):  
State Of The Art ◽  
Syntactic Structure ◽  
Target Sentence ◽  
Training Data ◽  
Style Transfer ◽  
Original Meaning ◽  
Original Sentence ◽  
Proposed Model ◽  
The Cost ◽  
Paraphrase Generation

The problem of generating a set of diverse paraphrase sentences while (1) not compromising the original meaning of the original sentence, and (2) imposing diversity in various semantic aspects, such as a lexical or syntactic structure, is examined. Existing work on paraphrase generation has focused more on the former, and the latter was trained as a fixed style transfer, such as transferring from positive to negative sentiments, even at the cost of losing semantics. In this work, we consider style transfer as a means of imposing diversity, with a paraphrasing correctness constraint that the target sentence must remain a paraphrase of the original sentence. However, our goal is to maximize the diversity for a set of k generated paraphrases, denoted as the diversified paraphrase (DP) problem. Our key contribution is deciding the style guidance at generation towards the direction of increasing the diversity of output with respect to those generated previously. As pre-materializing training data for all style decisions is impractical, we train with biased data, but with debiasing guidance. Compared to state-of-the-art methods, our proposed model can generate more diverse and yet semantically consistent paraphrase sentences. That is, our model, trained with the MSCOCO dataset, achieves the highest embedding scores, .94/.95/.86, similar to state-of-the-art results, but with a lower mBLEU score (more diverse) by 8.73%.

scholarly journals GTAE: Graph Transformer–Based Auto-Encoders for Linguistic-Constrained Text Style Transfer

2021 ◽  
Vol 12 (3) ◽  
pp. 1-16
Author(s):  
Yukai Shi ◽  
Sen Zhang ◽  
Chenxing Zhou ◽  
Xiaodan Liang ◽  
Xiaojun Yang ◽  
...  
Keyword(s):  
Deep Neural Networks ◽  
Model Space ◽  
Style Transfer ◽  
Unconstrained Model ◽  
Linguistic Rules ◽  
Comparable Performance ◽  
Parallel Text ◽  
Content Preservation ◽  
Transfer Tasks ◽  
Transfer Accuracy

Non-parallel text style transfer has attracted increasing research interests in recent years. Despite successes in transferring the style based on the encoder-decoder framework, current approaches still lack the ability to preserve the content and even logic of original sentences, mainly due to the large unconstrained model space or too simplified assumptions on latent embedding space. Since language itself is an intelligent product of humans with certain grammars and has a limited rule-based model space by its nature, relieving this problem requires reconciling the model capacity of deep neural networks with the intrinsic model constraints from human linguistic rules. To this end, we propose a method called Graph Transformer–based Auto-Encoder, which models a sentence as a linguistic graph and performs feature extraction and style transfer at the graph level, to maximally retain the content and the linguistic structure of original sentences. Quantitative experiment results on three non-parallel text style transfer tasks show that our model outperforms state-of-the-art methods in content preservation, while achieving comparable performance on transfer accuracy and sentence naturalness.

scholarly journals Encryption Algorithm of Multiple-Image Using Mixed Image Elements and Two Dimensional Chaotic Economic Map

Entropy ◽  
2018 ◽  
Vol 20 (10) ◽  
pp. 801 ◽  
Author(s):  
A. Karawia
Keyword(s):  
Logistic Map ◽  
Experimental Results ◽  
Encryption Algorithm ◽  
Current Work ◽  
Two Dimensional ◽  
Huge Number ◽  
Multiple Images ◽  
Encrypted Image ◽  
Multiple Image

To enhance the encryption proficiency and encourage the protected transmission of multiple images, the current work introduces an encryption algorithm for multiple images using the combination of mixed image elements (MIES) and a two-dimensional economic map. Firstly, the original images are grouped into one big image that is split into many pure image elements (PIES); secondly, the logistic map is used to shuffle the PIES; thirdly, it is confused with the sequence produced by the two-dimensional economic map to get MIES; finally, the MIES are gathered into a big encrypted image that is split into many images of the same size as the original images. The proposed algorithm includes a huge number key size space, and this makes the algorithm secure against hackers. Even more, the encryption results obtained by the proposed algorithm outperform existing algorithms in the literature. A comparison between the proposed algorithm and similar algorithms is made. The analysis of the experimental results and the proposed algorithm shows that the proposed algorithm is efficient and secure.

scholarly journals Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning

2020 ◽  
Vol 34 (05) ◽  
pp. 8376-8383
Author(s):  
Dayiheng Liu ◽  
Jie Fu ◽  
Yidan Zhang ◽  
Chris Pal ◽  
Jiancheng Lv
Keyword(s):  
Experimental Studies ◽  
Target Sentence ◽  
Sentence Length ◽  
Adversarial Learning ◽  
Style Transfer ◽  
Continuous Space ◽  
Fine Grained ◽  
Gradient Based ◽  
Transfer Tasks ◽  
New Framework

Typical methods for unsupervised text style transfer often rely on two key ingredients: 1) seeking the explicit disentanglement of the content and the attributes, and 2) troublesome adversarial learning. In this paper, we show that neither of these components is indispensable. We propose a new framework that utilizes the gradients to revise the sentence in a continuous space during inference to achieve text style transfer. Our method consists of three key components: a variational auto-encoder (VAE), some attribute predictors (one for each attribute), and a content predictor. The VAE and the two types of predictors enable us to perform gradient-based optimization in the continuous space, which is mapped from sentences in a discrete space, to find the representation of a target sentence with the desired attributes and preserved content. Moreover, the proposed method naturally has the ability to simultaneously manipulate multiple fine-grained attributes, such as sentence length and the presence of specific words, when performing text style transfer tasks. Compared with previous adversarial learning based methods, the proposed method is more interpretable, controllable and easier to train. Extensive experimental studies on three popular text style transfer tasks show that the proposed method significantly outperforms five state-of-the-art methods.

scholarly journals Parkinson’s Disease EMG Data Augmentation and Simulation with DCGANs and Style Transfer

Sensors ◽  
2020 ◽  
Vol 20 (9) ◽  
pp. 2605 ◽  
Author(s):  
Rafael Anicet Zanini ◽  
Esther Luna Colombini
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Data Augmentation ◽  
Experimental Results ◽  
Generative Adversarial Networks ◽  
Style Transfer ◽  
Treatment Approaches ◽  
Adversarial Networks

This paper proposes two new data augmentation approaches based on Deep Convolutional Generative Adversarial Networks (DCGANs) and Style Transfer for augmenting Parkinson’s Disease (PD) electromyography (EMG) signals. The experimental results indicate that the proposed models can adapt to different frequencies and amplitudes of tremor, simulating each patient’s tremor patterns and extending them to different sets of movement protocols. Therefore, one could use these models for extending the existing patient dataset and generating tremor simulations for validating treatment approaches on different movement scenarios.

scholarly journals Consistent Video Style Transfer via Compound Regularization

2020 ◽  
Vol 34 (07) ◽  
pp. 12233-12240
Author(s):  
Wenjing Wang ◽  
Jizheng Xu ◽  
Li Zhang ◽  
Yue Wang ◽  
Jiaying Liu
Keyword(s):  
State Of The Art ◽  
Video Data ◽  
Experimental Results ◽  
Temporal Consistency ◽  
Challenging Problem ◽  
Style Transfer ◽  
Single Frame ◽  
Optical Flows ◽  
Training Strategies ◽  
Art Style

Recently, neural style transfer has drawn many attentions and significant progresses have been made, especially for image style transfer. However, flexible and consistent style transfer for videos remains a challenging problem. Existing training strategies, either using a significant amount of video data with optical flows or introducing single-frame regularizers, have limited performance on real videos. In this paper, we propose a novel interpretation of temporal consistency, based on which we analyze the drawbacks of existing training strategies; and then derive a new compound regularization. Experimental results show that the proposed regularization can better balance the spatial and temporal performance, which supports our modeling. Combining with the new cost formula, we design a zero-shot video style transfer framework. Moreover, for better feature migration, we introduce a new module to dynamically adjust inter-channel distributions. Quantitative and qualitative results demonstrate the superiority of our method over other state-of-the-art style transfer methods. Our project is publicly available at: https://daooshee.github.io/CompoundVST/.

scholarly journals Peringkasan Dokumen Berdasarkan Metode Semantic Sebaran Kalimat

2017 ◽  
Vol 8 (1) ◽  
Author(s):  
Aminul Wahib ◽  
Dita Lupita Sari
Keyword(s):  
Semantic Relation ◽  
Experimental Results ◽  
Semantic Meaning ◽  
Distribution Method ◽  
Average Performance ◽  
Search Results ◽  
Abstract Sentence ◽  
New Strategies

Abstract. Sentence distribution method performs weighting based on the sentence distribution without taking the semantic meaning of the sentence spread into account. In fact, the semantic relation between sentences is believed to increase the relevance of the search results document. This study proposes new strategies to summarize documents using the semantic sentence distribution method in an effort to improve the quality of the summary. The experimental results show that the proposed method has better performance with the average performance ROUGE-1 0.412, an increase of 1,9% compared to "Sentence distribution method" and ROUGE-2 by 4,7% compared to 0.127 "sentence distribution method".Keywords: Semantic Sentence Distribution, Summarizing Document, ROUGE. Abstrak. Peringkasan dokumen menggunakan metode sebaran kalimat terbukti memiliki hasil yang lebih baik jika dibanding dengan penelitian-penelitian sebelumnya. Metode tersebut melakukan pembobotan kalimat berdasarkan sebaran kalimat tanpa memperhitungkan makna semantic kalimat yang tersebar. Faktanya hubungan semantic antar kalimat telah terbukti mampu meningkatkan relevansi hasil dalam pencarian dokumen. Penelitian ini mengajukan strategi baru dalam peringkasan dokumen yaitu menggunakan metode semantic sebaran kalimat sebagai upaya untuk meningkatkan kualitas hasil ringkasan. Hasil eksperimen didapatkan bahwa metode yang diusulkan memiliki performa lebih baik dengan capaian rata-rata ROUGE-1 0,412, meningkat 1,9% dibanding metode sebaran kalimat dan ROUGE-2 0,127 meningkat 4,7% dibanding metode sebaran kalimat.Kata Kunci: Semantic Sebaran Kalimat, Peringkasan Dokumen, ROUGE.

scholarly journals From Reality to Perception: Genre-Based Neural Image Style Transfer

2018 ◽  
Author(s):  
Zhuoqi Ma ◽  
Nannan Wang ◽  
Xinbo Gao ◽  
Jie Li
Keyword(s):  
Transfer Process ◽  
Real World ◽  
Experimental Results ◽  
Style Transfer ◽  
The Real ◽  
Design Aspect ◽  
Semantic Correspondence

We introduce a novel thought for integrating artists’ perceptions on the real world into neural image style transfer process. Conventional approaches commonly migrate color or texture patterns from style image to content image, but the underlying design aspect of the artist always get overlooked. We want to address the in-depth genre style, that how artists perceive the real world and express their perceptions in the artwork. We collect a set of Van Gogh’s paintings and cubist artworks, and their semantically corresponding real world photos. We present a novel genre style transfer framework modeled after the mechanism of actual artwork production. The target style representation is reconstructed based on the semantic correspondence between real world photo and painting, which enable the perception guidance in style transfer. The experimental results demonstrate that our method can capture the overall style of a genre or an artist. We hope that this work provides new insight for including artists’ perceptions into neural style transfer process, and helps people to understand the underlying characters of the artist or the genre.

Nonlinear Dynamics of Nonlinear L-Shape Piezoelectric Systems for Positive and Reverse Sweep Waveform

2019 ◽  
Author(s):  
Ming Hui Yao
Keyword(s):  
Power Generation ◽  
Piezoelectric Layer ◽  
Great Influence ◽  
Experimental Results ◽  
Beam Power ◽  
Dynamic Behaviors ◽  
Piezoelectric Beam ◽  
Stiffness Characteristic ◽  
Generation Structure ◽  
The Relationship

Abstract This paper presents a bistable inverted L-shaped piezoelectric beam power generation structure, and its dynamic behaviors and power generation performance are studied by positive and reverse sweep waveform experiments. The piezoelectric beam includes the substructure layer and the piezoelectric layer. The material of the piezoelectric layer is the piezoelectric ceramic transducer (PZT), and the material of the substructure layer is the phosphor brass. The positive and reverse sinusoidal excitation signal is selected. The snap through phenomenon and stiffness characteristic of the system are investigated by experimental results of the positive and reverse sweep waveform. The relationship between dynamic behaviors and electrical behaviors of the system is also studied. Experimental results show that the positive and reverse sweep waveform has a great influence on vibration of the nonlinear system. Due to the hard spring characteristic of the system, the large vibration amplitude is easy to appear in the positive sweep waveform. Dynamic behaviors of the piezoelectric system are related to its electrical behaviors. When dynamic behaviors bifurcate, electrical behaviors bifurcate. These results can be applied to explore the vibration characteristic and the power generation of the nonlinear piezoelectric system.

Sign in / Sign up

Export Citation Format

Share Document