paper-with-me

Papers

Deconvolutional Paragraph Representation Learning

2017-08-16 · NeurIPS 2017 12 · Yizhe Zhang, Dinghan Shen, Guoyin Wang, Zhe Gan, Ricardo Henao, Lawrence Carin

Learning latent representations from long text sequences is an important first step in many natural language processing applications. Recurrent Neural Networks (RNNs) have become a cornerstone for this challenging task. However, the quality of sentences during RNN-based decoding (reconstruction) decreases with the length of the text. We propose a sequence-to-sequence, purely convolutional and deconvolutional autoencoding framework that is free of the above issue, while also being computationally efficient. The proposed method is simple, easy to implement and can be leveraged as a building block for many applications. We show empirically that compared to RNNs, our framework is better at reconstructing and correcting long paragraphs. Quantitative evaluation on semi-supervised text classification and summarization tasks demonstrate the potential for better utilization of long unlabeled text data.

📄 PDF Abstract BibTeX arXiv:1708.04729

Code (4)

dreasysnail/deconv_paragraph_represention tf
dreasysnail/textGAN_public tf
smalik169/recursive-convolutional-autoencoder pytorch
tuvuumass/SCoPE tf

Tasks

General ClassificationRepresentation LearningSemi-Supervised Text ClassificationText Classification

Similar Papers 제목 키워드 기반

Convolutional Auto-encoding of Sentence Topics for Image Paragraph Generation

2019-08-01 · Jing Wang, Yingwei Pan, Ting Yao, Jinhui Tang 외

Image paragraph generation is the task of producing a coherent story (usually a paragraph) that describes the visual content of an image. The problem nevertheless is not trivial especially when there are multiple descrip…

DescriptiveImage Paragraph CaptioningSentencevalid

Graph Autoencoders with Deconvolutional Networks

2020-12-22 · Jia Li, Tomas Yu, Da-Cheng Juan, Arjun Gopalan 외

Recent studies have indicated that Graph Convolutional Networks (GCNs) act as a \emph{low pass} filter in spectral domain and encode smoothed node representations. In this paper, we consider their opposite, namely Graph …

Graph Generation

Learning Common and Specific Features for RGB-D Semantic Segmentation with Deconvolutional Networks

2016-08-03 · Jinghua Wang, Zhenhua Wang, DaCheng Tao, Simon See 외

In this paper, we tackle the problem of RGB-D semantic segmentation of indoor images. We take advantage of deconvolutional networks which can predict pixel-wise class labels, and develop a new structure for deconvolution…

SegmentationSemantic Segmentation

Deconvolutional Networks on Graph Data

2021-10-29 · NeurIPS 2021 12 · Jia Li, Jiajin Li, Yang Liu, Jianwei Yu 외

In this paper, we consider an inverse problem in graph learning domain -- ``given the graph representations smoothed by Graph Convolutional Network (GCN), how can we reconstruct the input graph signal?" We propose Graph …

Graph LearningImputation

Pixel Deconvolutional Networks

2017-05-18 · ICLR 2018 1 · Hongyang Gao, Hao Yuan, Zhengyang Wang, Shuiwang Ji

Deconvolutional layers have been widely used in a variety of deep models for up-sampling, including encoder-decoder networks for semantic segmentation and deep generative models for unsupervised learning. One of the key …

DecoderImage GenerationSegmentationSemantic Segmentation