paper-with-me

홈 › Papers

Balancing Effect of Training Dataset Distribution of Multiple Styles for Multi-Style Text Transfer

2023-05-24 · Debarati Das, David Ma, Dongyeop Kang

Text style transfer is an exciting task within the field of natural language generation that is often plagued by the need for high-quality paired datasets. Furthermore, training a model for multi-attribute text style transfer requires datasets with sufficient support across all combinations of the considered stylistic attributes, adding to the challenges of training a style transfer model. This paper explores the impact of training data input diversity on the quality of the generated text from the multi-style transfer model. We construct a pseudo-parallel dataset by devising heuristics to adjust the style distribution in the training samples. We balance our training dataset using marginal and joint distributions to train our style transfer models. We observe that a balanced dataset produces more effective control effects over multiple styles than an imbalanced or skewed one. Through quantitative analysis, we explore the impact of multiple style distributions in training data on style-transferred output. These findings will better inform the design of style-transfer datasets.

📄 PDF Abstract BibTeX arXiv:2305.15582

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeDiversityStyle TransferText GenerationText Style Transfer

Similar Papers 제목 키워드 기반

Deep Time-series Forecasting Needs Kernelized Moment Balancing

2026-01-31 · Licheng Pan, Hao Wang, Haocheng Yang, Yuqi Li 외 arxiv

Deep time-series forecasting can be formulated as a distribution balancing problem aimed at aligning the distribution of the forecasts and ground truths. According to Imbens' criterion, true distribution balance requires…

Revisiting Long-tailed Image Classification: Survey and Benchmarks with New Evaluation Metrics

2023-02-03 · Chaowei Fang, Dingwen Zhang, Wen Zheng, Xue Li 외

Recently, long-tailed image classification harvests lots of research attention, since the data distribution is long-tailed in many real-world situations. Piles of algorithms are devised to address the data imbalance prob…

image-classificationImage ClassificationLong-tail Learning

Stable Prediction across Unknown Environments

2018-06-16 · Kun Kuang, Ruoxuan Xiong, Peng Cui, Susan Athey 외

In many important machine learning applications, the training distribution used to learn a probabilistic classifier differs from the testing distribution on which the classifier will be used to make predictions. Traditio…

feature selectionPrediction

Class Balancing GAN with a Classifier in the Loop

2021-06-17 · Harsh Rangwani, Konda Reddy Mopuri, R. Venkatesh Babu

Generative Adversarial Networks (GANs) have swiftly evolved to imitate increasingly complex image distributions. However, majority of the developments focus on performance of GANs on balanced datasets. We find that the e…

Integrating Local Real Data with Global Gradient Prototypes for Classifier Re-Balancing in Federated Long-Tailed Learning

2023-01-25 · Wenkai Yang, Deli Chen, Hao Zhou, Fandong Meng 외

Federated Learning (FL) has become a popular distributed learning paradigm that involves multiple clients training a global model collaboratively in a data privacy-preserving manner. However, the data samples usually fol…

Federated LearningPrivacy Preserving