PyTorchKR Papers

최신 논문

총 9,642편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1905.08990공식 코드 · Papers with Code

MIST: A Novel Training Strategy for Low-latencyScalable Neural Net Decoders

In this paper, we propose a low latency, robust and scalable neural net based decoder for convolutional and low-density parity-check (LPDC) coding schemes. The proposed decoders are demonstrated to have bit error rate (BER) and block error rate (BLER) performances at par with the state-of-the-art neural net based decoders while achieving more than 8 times higher decoding speed. The enhanced decoding speed is due to the use of convolutional neural network (CNN) as opposed to recurrent neural network (RNN) used in the best known neural net based decoders. This contradicts existing doctrine that only RNN based decoders can provide a performance close to the optimal ones. The key ingredient to our approach is a novel Mixed-SNR Independent Samples based Training (MIST), which allows for training of CNN with only 1\% of possible datawords, even for block length as high as 1000. The proposed decoder is robust as, once trained, the same decoder can be used for a wide range of SNR values. Finally, in the presence of channel outages, the proposed decoders outperform the best known decoders, {\it viz.} unquantized Viterbi decoder for convolutional code, and belief propagation for LDPC. This gives the CNN decoder a significant advantage in 5G millimeter wave systems, where channel outages are prevalent.

arXiv:1905.08929

Learning Fully Dense Neural Networks for Image Semantic Segmentation

Semantic segmentation is pixel-wise classification which retains critical spatial information. The "feature map reuse" has been commonly adopted in CNN based approaches to take advantage of feature maps in the early layers for the later spatial reconstruction. Along this direction, we go a step further by proposing a fully dense neural network with an encoder-decoder structure that we abbreviate as FDNet. For each stage in the decoder module, feature maps of all the previous blocks are adaptively aggregated to feed-forward as input. On the one hand, it reconstructs the spatial boundaries accurately. On the other hand, it learns more efficiently with the more efficient gradient backpropagation. In addition, we propose the boundary-aware loss function to focus more attention on the pixels near the boundary, which boosts the "hard examples" labeling. We have demonstrated the best performance of the FDNet on the two benchmark datasets: PASCAL VOC 2012, NYUDv2 over previous works when not considering training on other datasets.

arXiv:1905.08836공식 코드 · Papers with Code

Sample Efficient Text Summarization Using a Single Pre-Trained Transformer

Language model (LM) pre-training has resulted in impressive performance and sample efficiency on a variety of language understanding tasks. However, it remains unclear how to best use pre-trained LMs for generation tasks such as abstractive summarization, particularly to enhance sample efficiency. In these sequence-to-sequence settings, prior work has experimented with loading pre-trained weights into the encoder and/or decoder networks, but used non-pre-trained encoder-decoder attention weights. We instead use a pre-trained decoder-only network, where the same Transformer LM both encodes the source and generates the summary. This ensures that all parameters in the network, including those governing attention over source states, have been pre-trained before the fine-tuning step. Experiments on the CNN/Daily Mail dataset show that our pre-trained Transformer LM substantially improves over pre-trained Transformer encoder-decoder networks in limited-data settings. For instance, it achieves 13.1 ROUGE-2 using only 1% of the training data (~3000 examples), while pre-trained encoder-decoder models score 2.3 ROUGE-2.

arXiv:1905.09263

FastSpeech: Fast, Robust and Controllable Text to Speech

Neural network based end-to-end text to speech (TTS) has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron 2) usually first generate mel-spectrogram from text, and then synthesize speech from the mel-spectrogram using vocoder such as WaveNet. Compared with traditional concatenative and statistical parametric approaches, neural network based end-to-end models suffer from slow inference speed, and the synthesized speech is usually not robust (i.e., some words are skipped or repeated) and lack of controllability (voice speed or prosody control). In this work, we propose a novel feed-forward network based on Transformer to generate mel-spectrogram in parallel for TTS. Specifically, we extract attention alignments from an encoder-decoder based teacher model for phoneme duration prediction, which is used by a length regulator to expand the source phoneme sequence to match the length of the target mel-spectrogram sequence for parallel mel-spectrogram generation. Experiments on the LJSpeech dataset show that our parallel model matches autoregressive models in terms of speech quality, nearly eliminates the problem of word skipping and repeating in particularly hard cases, and can adjust voice speed smoothly. Most importantly, compared with autoregressive Transformer TTS, our model speeds up mel-spectrogram generation by 270x and the end-to-end speech synthesis by 38x. Therefore, we call our model FastSpeech.

arXiv:1905.08622공식 코드 · Papers with Code

Variational Hetero-Encoder Randomized GANs for Joint Image-Text Modeling

For bidirectional joint image-text modeling, we develop variational hetero-encoder (VHE) randomized generative adversarial network (GAN), a versatile deep generative model that integrates a probabilistic text decoder, probabilistic image encoder, and GAN into a coherent end-to-end multi-modality learning framework. VHE randomized GAN (VHE-GAN) encodes an image to decode its associated text, and feeds the variational posterior as the source of randomness into the GAN image generator. We plug three off-the-shelf modules, including a deep topic model, a ladder-structured image encoder, and StackGAN++, into VHE-GAN, which already achieves competitive performance. This further motivates the development of VHE-raster-scan-GAN that generates photo-realistic images in not only a multi-scale low-to-high-resolution manner, but also a hierarchical-semantic coarse-to-fine fashion. By capturing and relating hierarchical semantic and visual concepts with end-to-end training, VHE-raster-scan-GAN achieves state-of-the-art performance in a wide variety of image-text multi-modality learning and generation tasks.

arXiv:1905.08454

A Seq-to-Seq Transformer Premised Temporal Convolutional Network for Chinese Word Segmentation

The prevalent approaches of Chinese word segmentation task almost rely on the Bi-LSTM neural network. However, the methods based the Bi-LSTM have some inherent drawbacks: hard to parallel computing, little efficient in applying the Dropout method to inhibit the Overfitting and little efficient in capturing the character information at the more distant site of a long sentence for the word segmentation task. In this work, we propose a sequence-to-sequence transformer model for Chinese word segmentation, which is premised a type of convolutional neural network named temporal convolutional network. The model uses the temporal convolutional network to construct an encoder, and uses one layer of fully-connected neural network to build a decoder, and applies the Dropout method to inhibit the Overfitting, and captures the character information at the distant site of a sentence by adding the layers of the encoder, and binds Conditional Random Fields model to train parameters, and uses the Viterbi algorithm to infer the final result of the Chinese word segmentation. The experiments on traditional Chinese corpora and simplified Chinese corpora show that the performance of Chinese word segmentation of the model is equivalent to the performance of the methods based the Bi-LSTM, and the model has a tremendous growth in parallel computing than the models based the Bi-LSTM.

arXiv:1905.08407

Generating Logical Forms from Graph Representations of Text and Entities

Structured information about entities is critical for many semantic parsing tasks. We present an approach that uses a Graph Neural Network (GNN) architecture to incorporate information about relevant entities and their relations during parsing. Combined with a decoder copy mechanism, this approach provides a conceptually simple mechanism to generate logical forms with entities. We demonstrate that this approach is competitive with the state-of-the-art across several tasks without pre-training, and outperforms existing approaches when combined with BERT pre-training.

arXiv:1905.07478

Dueling Decoders: Regularizing Variational Autoencoder Latent Spaces

Variational autoencoders learn unsupervised data representations, but these models frequently converge to minima that fail to preserve meaningful semantic information. For example, variational autoencoders with autoregressive decoders often collapse into autodecoders, where they learn to ignore the encoder input. In this work, we demonstrate that adding an auxiliary decoder to regularize the latent space can prevent this collapse, but successful auxiliary decoding tasks are domain dependent. Auxiliary decoders can increase the amount of semantic information encoded in the latent space and visible in the reconstructions. The semantic information in the variational autoencoder's representation is only weakly correlated with its rate, distortion, or evidence lower bound. Compared to other popular strategies that modify the training objective, our regularization of the latent space generally increased the semantic information content.

arXiv:1905.07443

AutoDispNet: Improving Disparity Estimation With AutoML

Much research work in computer vision is being spent on optimizing existing network architectures to obtain a few more percentage points on benchmarks. Recent AutoML approaches promise to relieve us from this effort. However, they are mainly designed for comparatively small-scale classification tasks. In this work, we show how to use and extend existing AutoML techniques to efficiently optimize large-scale U-Net-like encoder-decoder architectures. In particular, we leverage gradient-based neural architecture search and Bayesian optimization for hyperparameter search. The resulting optimization does not require a large-scale compute cluster. We show results on disparity estimation that clearly outperform the manually optimized baseline and reach state-of-the-art performance.

arXiv:1905.08110

Image Captioning based on Deep Learning Methods: A Survey

Image captioning is a challenging task and attracting more and more attention in the field of Artificial Intelligence, and which can be applied to efficient image retrieval, intelligent blind guidance and human-computer interaction, etc. In this paper, we present a survey on advances in image captioning based on Deep Learning methods, including Encoder-Decoder structure, improved methods in Encoder, improved methods in Decoder, and other improvements. Furthermore, we discussed future research directions.

arXiv:1905.07841

Multimodal Transformer with Multi-View Visual Representation for Image Captioning

Image captioning aims to automatically generate a natural language description of a given image, and most state-of-the-art models have adopted an encoder-decoder framework. The framework consists of a convolution neural network (CNN)-based image encoder that extracts region-based visual features from the input image, and an recurrent neural network (RNN)-based caption decoder that generates the output caption words based on the visual features with the attention mechanism. Despite the success of existing studies, current methods only model the co-attention that characterizes the inter-modal interactions while neglecting the self-attention that characterizes the intra-modal interactions. Inspired by the success of the Transformer model in machine translation, here we extend it to a Multimodal Transformer (MT) model for image captioning. Compared to existing image captioning approaches, the MT model simultaneously captures intra- and inter-modal interactions in a unified attention block. Due to the in-depth modular composition of such attention blocks, the MT model can perform complex multimodal reasoning and output accurate captions. Moreover, to further improve the image captioning performance, multi-view visual features are seamlessly introduced into the MT model. We quantitatively and qualitatively evaluate our approach using the benchmark MSCOCO image captioning dataset and conduct extensive ablation studies to investigate the reasons behind its effectiveness. The experimental results show that our method significantly outperforms the previous state-of-the-art methods. With an ensemble of seven models, our solution ranks the 1st place on the real-time leaderboard of the MSCOCO image captioning challenge at the time of the writing of this paper.

arXiv:1905.07195

CHiVE: Varying Prosody in Speech Synthesis with a Linguistically Driven Dynamic Hierarchical Conditional Variational Network

The prosodic aspects of speech signals produced by current text-to-speech systems are typically averaged over training material, and as such lack the variety and liveliness found in natural speech. To avoid monotony and averaged prosody contours, it is desirable to have a way of modeling the variation in the prosodic aspects of speech, so audio signals can be synthesized in multiple ways for a given text. We present a new, hierarchically structured conditional variational autoencoder to generate prosodic features (fundamental frequency, energy and duration) suitable for use with a vocoder or a generative model like WaveNet. At inference time, an embedding representing the prosody of a sentence may be sampled from the variational layer to allow for prosodic variation. To efficiently capture the hierarchical nature of the linguistic input (words, syllables and phones), both the encoder and decoder parts of the auto-encoder are hierarchical, in line with the linguistic structure, with layers being clocked dynamically at the respective rates. We show in our experiments that our dynamic hierarchical network outperforms a non-hierarchical state-of-the-art baseline, and, additionally, that prosody transfer across sentences is possible by employing the prosody embedding of one sentence to generate the speech signal of another.

arXiv:1905.07089공식 코드 · Papers with Code

Exact-K Recommendation via Maximal Clique Optimization

This paper targets to a novel but practical recommendation problem named exact-K recommendation. It is different from traditional top-K recommendation, as it focuses more on (constrained) combinatorial optimization which will optimize to recommend a whole set of K items called card, rather than ranking optimization which assumes that "better" items should be put into top positions. Thus we take the first step to give a formal problem definition, and innovatively reduce it to Maximum Clique Optimization based on graph. To tackle this specific combinatorial optimization problem which is NP-hard, we propose Graph Attention Networks (GAttN) with a Multi-head Self-attention encoder and a decoder with attention mechanism. It can end-to-end learn the joint distribution of the K items and generate an optimal card rather than rank individual items by prediction scores. Then we propose Reinforcement Learning from Demonstrations (RLfD) which combines the advantages in behavior cloning and reinforcement learning, making it sufficient- and-efficient to train the model. Extensive experiments on three datasets demonstrate the effectiveness of our proposed GAttN with RLfD method, it outperforms several strong baselines with a relative improvement of 7.7% and 4.7% on average in Precision and Hit Ratio respectively, and achieves state-of-the-art (SOTA) performance for the exact-K recommendation problem.

arXiv:1905.06597

A Simple Dual-decoder Model for Generating Response with Sentiment

How to generate human like response is one of the most challenging tasks for artificial intelligence. In a real application, after reading the same post different people might write responses with positive or negative sentiment according to their own experiences and attitudes. To simulate this procedure, we propose a simple but effective dual-decoder model to generate response with a particular sentiment, by connecting two sentiment decoders to one encoder. To support this model training, we construct a new conversation dataset with the form of (post, resp1, resp2) where two responses contain opposite sentiment. Experiment results show that our dual-decoder model can generate diverse responses with target sentiment, which obtains significant performance gain in sentiment accuracy and word diversity over the traditional single-decoder model. We will make our data and code publicly available for further study.

arXiv:1905.06596공식 코드 · Papers with Code

Joint Source-Target Self Attention with Locality Constraints

The dominant neural machine translation models are based on the encoder-decoder structure, and many of them rely on an unconstrained receptive field over source and target sequences. In this paper we study a new architecture that breaks with both conventions. Our simplified architecture consists in the decoder part of a transformer model, based on self-attention, but with locality constraints applied on the attention receptive field. As input for training, both source and target sentences are fed to the network, which is trained as a language model. At inference time, the target tokens are predicted autoregressively starting with the source sequence as previous tokens. The proposed model achieves a new state of the art of 35.7 BLEU on IWSLT'14 German-English and matches the best reported results in the literature on the WMT'14 English-German and WMT'14 English-French translation benchmarks.

arXiv:1905.06241공식 코드 · Papers with Code

Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing

Research on parsing language to SQL has largely ignored the structure of the database (DB) schema, either because the DB was very simple, or because it was observed at both training and test time. In Spider, a recently-released text-to-SQL dataset, new and complex DBs are given at test time, and so the structure of the DB schema can inform the predicted SQL query. In this paper, we present an encoder-decoder semantic parser, where the structure of the DB schema is encoded with a graph neural network, and this representation is later used at both encoding and decoding time. Evaluation shows that encoding the schema structure improves our parser accuracy from 33.8% to 39.4%, dramatically above the current state of the art, which is at 19.7%.

arXiv:1905.06147

Embeddings and Representation Learning for Structured Data

Performing machine learning on structured data is complicated by the fact that such data does not have vectorial form. Therefore, multiple approaches have emerged to construct vectorial representations of structured data, from kernel and distance approaches to recurrent, recursive, and convolutional neural networks. Recent years have seen heightened attention in this demanding field of research and several new approaches have emerged, such as metric learning on structured data, graph convolutional neural networks, and recurrent decoder networks for structured data. In this contribution, we provide an high-level overview of the state-of-the-art in representation learning and embeddings for structured data across a wide range of machine learning fields.

arXiv:1905.05178공식 코드 · Papers with Code

Graph U-Nets

We consider the problem of representation learning for graph data. Convolutional neural networks can naturally operate on images, but have significant challenges in dealing with graph data. Given images are special cases of graphs with nodes lie on 2D lattices, graph embedding tasks have a natural correspondence with image pixel-wise prediction tasks such as segmentation. While encoder-decoder architectures like U-Nets have been successfully applied on many image pixel-wise prediction tasks, similar methods are lacking for graph data. This is due to the fact that pooling and up-sampling operations are not natural on graph data. To address these challenges, we propose novel graph pooling (gPool) and unpooling (gUnpool) operations in this work. The gPool layer adaptively selects some nodes to form a smaller graph based on their scalar projection values on a trainable projection vector. We further propose the gUnpool layer as the inverse operation of the gPool layer. The gUnpool layer restores the graph into its original structure using the position information of nodes selected in the corresponding gPool layer. Based on our proposed gPool and gUnpool layers, we develop an encoder-decoder model on graph, known as the graph U-Nets. Our experimental results on node classification and graph classification tasks demonstrate that our methods achieve consistently better performance than previous models.

arXiv:1905.05621공식 코드 · Papers with Code

Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation

Disentangling the content and style in the latent space is prevalent in unpaired text style transfer. However, two major issues exist in most of the current neural models. 1) It is difficult to completely strip the style information from the semantics for a sentence. 2) The recurrent neural network (RNN) based encoder and decoder, mediated by the latent representation, cannot well deal with the issue of the long-term dependency, resulting in poor preservation of non-stylistic semantic content. In this paper, we propose the Style Transformer, which makes no assumption about the latent representation of source sentence and equips the power of attention mechanism in Transformer to achieve better style transfer and better content preservation.

arXiv:1905.05532

Atom Responding Machine for Dialog Generation

Recently, improving the relevance and diversity of dialogue system has attracted wide attention. For a post x, the corresponding response y is usually diverse in the real-world corpus, while the conventional encoder-decoder model tends to output the high-frequency (safe but trivial) responses and thus is difficult to handle the large number of responding styles. To address these issues, we propose the Atom Responding Machine (ARM), which is based on a proposed encoder-composer-decoder network trained by a teacher-student framework. To enrich the generated responses, ARM introduces a large number of molecule-mechanisms as various responding styles, which are conducted by taking different combinations from a few atom-mechanisms. In other words, even a little of atom-mechanisms can make a mickle of molecule-mechanisms. The experiments demonstrate diversity and quality of the responses generated by ARM. We also present generating process to show underlying interpretability for the result.