paper-with-me

Papers

Improving Disentangled Text Representation Learning with Information-Theoretic Guidance

2020-06-01 · ACL 2020 6 · Pengyu Cheng, Martin Renqiang Min, Dinghan Shen, Christopher Malon, Yizhe Zhang, Yitong Li, Lawrence Carin

Learning disentangled representations of natural language is essential for many NLP tasks, e.g., conditional text generation, style transfer, personalized dialogue systems, etc. Similar problems have been studied extensively for other forms of data, such as images and videos. However, the discrete nature of natural language makes the disentangling of textual representations more challenging (e.g., the manipulation over the data space cannot be easily achieved). Inspired by information theory, we propose a novel method that effectively manifests disentangled representations of text, without any supervision on semantics. A new mutual information upper bound is derived and leveraged to measure dependence between style and content. By minimizing this upper bound, the proposed method induces style and content embeddings into two independent low-dimensional spaces. Experiments on both conditional text generation and text-style transfer demonstrate the high quality of our disentangled representation in terms of content and style preservation.

📄 PDF Abstract BibTeX arXiv:2006.00693

Code (0)

등록된 구현이 없습니다.

Tasks

Conditional Text GenerationRepresentation LearningStyle TransferText GenerationText Style Transfer

Similar Papers 제목 키워드 기반

Disentangled Text Representation Learning with Information-Theoretic Perspective for Adversarial Robustness

2022-10-26 · Jiahao Zhao, Wenji Mao

Adversarial vulnerability remains a major obstacle to constructing reliable NLP systems. When imperceptible perturbations are added to raw input text, the performance of a deep learning model may drop dramatically under …

Adversarial RobustnessRepresentation Learningtext-classificationText Classification

Disentangled Representation Learning with Transmitted Information Bottleneck

2023-11-03 · Zhuohang Dang, Minnan Luo, Chengyou Jia, Guang Dai 외

Encoding only the task-related information from the raw data, \ie, disentangled representation learning, can greatly contribute to the robustness and generalizability of models. Although significant advances have been ma…

DisentanglementRepresentation LearningVariational Inference

Comparison Reveals Commonality: Customized Image Generation through Contrastive Inversion

2025-08-11 · Minseo Kim, Minchan Kwon, Dongyeun Lee, Yunho Jeon 외 arxiv

The recent demand for customized image generation raises a need for techniques that effectively extract the common concept from small sets of images. Existing methods typically rely on additional guidance, such as text p…

Contrastive LearningImage Generation

Improving Zero-shot Voice Style Transfer via Disentangled Representation Learning

2021-03-17 · ICLR 2021 1 · Siyang Yuan, Pengyu Cheng, Ruiyi Zhang, Weituo Hao 외

Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker. Previous works have made progress on voice conversion with parallel …

DecoderRepresentation LearningStyle TransferVoice Conversion

Disentangled Representations using Trained Models

2021-09-29 · Eva Smit, Thomas Gärtner, Patrick Forré

We propose a novel method to learn disentangled representations. The ability to compute a disentangled representation is useful for many tasks because it contains information about samples from a dataset in an interpreta…