SE-DAE: Style-Enhanced Denoising Auto-Encoder for Unsupervised Text Style Transfer

Li, Jicheng; Feng, Yang; Ou, Jiao

doi:10.1109/ijcnn52387.2021.9533731

Cited by 2 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this experiment, we only use one part of the data at a time (positive/negative), never using the human-labelled targets for a given example. We harness the power of reconstruction of the input using an auto-encoder (AE) (Shen et al, 2017;Li et al, 2021) and back-translation (BT) (Prabhumoye et al, 2018;Mukherjee et al, 2022). In the BT process, for English sentences, we perform a cycle of translation, using English-to-Banglato-English, while for Bangla sentences, we apply Bangla-to-English-to-Bangla translation.…”

Section: Non-parallel Style Transfermentioning

confidence: 99%

Low-Resource Text Style Transfer for Bangla: Data & Models

Mukherjee,

Bansal,

Majumdar

et al. 2023

Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)

View full text Add to dashboard Cite

Text style transfer (TST) involves modifying the linguistic style of a given text while retaining its core content. This paper addresses the challenging task of text style transfer in the Bangla language, which is low-resourced in this area. We present a novel Bangla dataset that facilitates text sentiment transfer, a subtask of TST, enabling the transformation of positive sentiment sentences to negative and vice versa. To establish a high-quality base for further research, we refined and corrected an existing English dataset of 1,000 sentences for sentiment transfer based on Yelp reviews, and we introduce a new human-translated Bangla dataset that parallels its English counterpart. Furthermore, we offer multiple benchmark models that serve as a validation of the dataset and baseline for further research.

show abstract

Section: Non-parallel Style Transfermentioning

confidence: 99%

Low-Resource Text Style Transfer for Bangla: Data & Models

Mukherjee,

Bansal,

Majumdar

et al. 2023

Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)

View full text Add to dashboard Cite

show abstract

“…Literature [14] proposed a deep learning method with strong learning ability to extract abstract features of signals. Literature [15] proposed a DAE, which is an unsupervised depth learning model. Due to the strong feature extraction ability of DAE, they are widely used in image classification, fault diagnosis, image denoising and other fields.…”

Section: Introductionmentioning

confidence: 99%

Research on pipeline inspection gauges localization based on residual denoising autoencoder

Guo,

Song,

Zeng

et al. 2023

Eng. Res. Express

View full text Add to dashboard Cite

To improve pipeline transportation efficiency, long-distance pipelines need to be cleaned regularly. Pipeline inspection gauges (PIGs) are widely used in pigging operations. The traditional PIG localization method generally has a large error and cannot achieve continuous tracking. To solve the problem of PIG real-time tracking and localization, this paper proposes a method of PIG localization for oil pipelines based on a denoising autoencoder(DAE). The attention deconvolution residual block (ADR) is introduced in the decoder part of the DAE, so that this model can learn and use global information to selectively emphasize key features, suppress useless features, and improve the noise removal performance of the model. After denoising, the negative pressure wave(NPW) signal is normalized, the time delay is extracted, and the PIG is located using the NPW localization formula. Experiments show that this method can effectively achieve real-time PIG localization. Compared with the EMD and DAE positioning methods, the relative positioning accuracy is increased by 3.5 times and 8.4 times, respectively.

show abstract

SE-DAE: Style-Enhanced Denoising Auto-Encoder for Unsupervised Text Style Transfer

Cited by 2 publications

References 19 publications

Low-Resource Text Style Transfer for Bangla: Data & Models

Low-Resource Text Style Transfer for Bangla: Data & Models

Research on pipeline inspection gauges localization based on residual denoising autoencoder

Contact Info

Product

Resources

About