codertimo / paper-log

읽어야 하는 논문들을 관리하고, 읽은 논문들의 기록을 남기는 공간
31 stars 5 forks source link

Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation #18

Closed codertimo closed 4 years ago

codertimo commented 4 years ago

어떤 내용의 논문인가요? 👋

Abstract (요약) 🕵🏻‍♂️

Unsupervised text attribute transfer automatically transforms a text to alter a specific attribute (e.g. sentiment) without using any parallel data, while simultaneously preserving its attribute-independent content. The dominant approaches are trying to model the content-independent attribute separately, e.g., learning different attributes' representations or using multiple attribute-specific decoders. However, it may lead to inflexibility from the perspective of controlling the degree of transfer or transferring over multiple aspects at the same time. To address the above problems, we propose a more flexible unsupervised text attribute transfer framework which replaces the process of modeling attribute with minimal editing of latent representations based on an attribute classifier. Specifically, we first propose a Transformer-based autoencoder to learn an entangled latent representation for a discrete text, then we transform the attribute transfer task to an optimization problem and propose the Fast-Gradient-Iterative-Modification algorithm to edit the latent representation until conforming to the target attribute. Extensive experimental results demonstrate that our model achieves very competitive performance on three public data sets. Furthermore, we also show that our model can not only control the degree of transfer freely but also allow to transfer over multiple aspects at the same time.

이 논문을 읽어서 무엇을 배울 수 있는지 알려주세요! 🤔

레퍼런스의 URL을 알려주세요! 🔗

https://arxiv.org/abs/1905.12926

codertimo commented 4 years ago

Motivation

Method

Novelty

다만 본 논문이 #19 과 매우 동일하다는 점에 있어서 novelty 에 대한 의심이 있습니다. 두 논문중 어떤 논문이 먼저 이 아이디어를 메인으로 사용하였는지는 분석을 해 봐야겠지만 전체적인 컨셉이나 방법이 비슷하다고 느껴집니다. (두 논문에서 메인으로 주장하는 부분이 inference 시에 variational latent variable 을 원하는 style 을 갖도록 style classifier 를 이용해 optimize 하는 방식을 사용하고 있기 때문입니다)