paper-with-me

홈 › Papers

Unsupervised Natural Language Generation with Denoising Autoencoders

2018-04-21 · EMNLP 2018 10 · Markus Freitag, Scott Roy

Generating text from structured data is important for various tasks such as question answering and dialog systems. We show that in at least one domain, without any supervision and only based on unlabeled text, we are able to build a Natural Language Generation (NLG) system with higher performance than supervised approaches. In our approach, we interpret the structured data as a corrupt representation of the desired output and use a denoising auto-encoder to reconstruct the sentence. We show how to introduce noise into training examples that do not contain structured data, and that the resulting denoising auto-encoder generalizes to generate correct sentences when given structured data.

📄 PDF Abstract BibTeX arXiv:1804.07899

Code (1)

mcleonard/NLG_Autoencoder pytorch

Tasks

DenoisingQuestion AnsweringSentenceText Generation

Similar Papers 제목 키워드 기반

Denoising Improves Latent Space Geometry in Text Autoencoders

2019-09-25 · Tianxiao Shen, Jonas Mueller, Regina Barzilay, Tommi Jaakkola

Neural language models have recently shown impressive gains in unconditional text generation, but controllable generation and manipulation of text remain challenging. In particular, controlling text via latent space oper…

DenoisingSentenceText Generation

Semi-Supervised Text Simplification with Back-Translation and Asymmetric Denoising Autoencoders

2020-04-30 · Yanbin Zhao, Lu Chen, Zhi Chen, Kai Yu

Text simplification (TS) rephrases long sentences into simplified variants while preserving inherent semantics. Traditional sequence-to-sequence models heavily rely on the quantity and quality of parallel sentences, whic…

DenoisingLanguage ModelingLanguage ModellingMachine Translation+4

Bilingual-GAN: A Step Towards Parallel Text Generation

2019-04-09 · WS 2019 6 · Ahmad Rashid, Alan Do-Omri, Md. Akmal Haidar, Qun Liu 외

Latent space based GAN methods and attention based sequence to sequence models have achieved impressive results in text generation and unsupervised machine translation respectively. Leveraging the two domains, we propose…

DecoderDenoisingMachine TranslationText Generation+2

Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders

2020-06-10 · ICLR 2021 1 · Mangal Prakash, Alexander Krull, Florian Jug

Deep Learning based methods have emerged as the indisputable leaders for virtually all image restoration tasks. Especially in the domain of microscopy images, various content-aware image restoration (CARE) approaches are…

Cell SegmentationDenoisingDiversityImage Restoration+2

Analyzing noise in autoencoders and deep networks

2014-06-06 · Ben Poole, Jascha Sohl-Dickstein, Surya Ganguli

Autoencoders have emerged as a useful framework for unsupervised learning of internal representations, and a wide variety of apparently conceptually disparate regularization techniques have been proposed to generate usef…

Denoising