PyTorchKR Papers

최신 논문

총 9,642편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1804.07891

A Deep Learning Approach for Forecasting Air Pollution in South Korea Using LSTM

Tackling air pollution is an imperative problem in South Korea, especially in urban areas, over the last few years. More specially, South Korea has joined the ranks of the world's most polluted countries alongside with other Asian capitals, such as Beijing or Delhi. Much research is being conducted in environmental science to evaluate the dangerous impact of particulate matters on public health. Besides that, deterministic models of air pollutant behavior are also generated; however, this is both complex and often inaccurate. On the contrary, deep recurrent neural network reveals potent potential on forecasting out-comes of time-series data and has become more prevalent. This paper uses Recurrent Neural Network (RNN) with Long Short-Term Memory units as a framework for leveraging knowledge from time-series data of air pollution and meteorological information in Daegu, Seoul, Beijing, and Shenyang. Additionally, we use encoder-decoder model, which is similar to machine comprehension problems, as a crucial part of our prediction machine. Finally, we investigate the prediction accuracy of various configurations. Our experiments prevent the efficiency of integrating multiple layers of RNN on prediction model when forecasting far timesteps ahead. This research is a significant motivation for not only continuing researching on urban air quality but also help the government leverage that insight to enact beneficial policies

arXiv:1805.04843공식 코드 · Papers with Code

Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders

Asking good questions in large-scale, open-domain conversational systems is quite significant yet rather untouched. This task, substantially different from traditional question generation, requires to question not only with various patterns but also on diverse and relevant topics. We observe that a good question is a natural composition of {\it interrogatives}, {\it topic words}, and {\it ordinary words}. Interrogatives lexicalize the pattern of questioning, topic words address the key information for topic transition in dialogue, and ordinary words play syntactical and grammatical roles in making a natural sentence. We devise two typed decoders (\textit{soft typed decoder} and \textit{hard typed decoder}) in which a type distribution over the three types is estimated and used to modulate the final generation distribution. Extensive experiments show that the typed decoders outperform state-of-the-art baselines and can generate more meaningful questions.

arXiv:1805.06771공식 코드 · Papers with Code

Convolutional Social Pooling for Vehicle Trajectory Prediction

Forecasting the motion of surrounding vehicles is a critical ability for an autonomous vehicle deployed in complex traffic. Motion of all vehicles in a scene is governed by the traffic context, i.e., the motion and relative spatial configuration of neighboring vehicles. In this paper we propose an LSTM encoder-decoder model that uses convolutional social pooling as an improvement to social pooling layers for robustly learning interdependencies in vehicle motion. Additionally, our model outputs a multi-modal predictive distribution over future trajectories based on maneuver classes. We evaluate our model using the publicly available NGSIM US-101 and I-80 datasets. Our results show improvement over the state of the art in terms of RMS values of prediction error and negative log-likelihoods of true future trajectories under the model's predictive distribution. We also present a qualitative analysis of the model's predicted distributions for various traffic scenarios.

arXiv:1805.03832

A comparable study of modeling units for end-to-end Mandarin speech recognition

End-To-End speech recognition have become increasingly popular in mandarin speech recognition and achieved delightful performance. Mandarin is a tonal language which is different from English and requires special treatment for the acoustic modeling units. There have been several different kinds of modeling units for mandarin such as phoneme, syllable and Chinese character. In this work, we explore two major end-to-end models: connectionist temporal classification (CTC) model and attention based encoder-decoder model for mandarin speech recognition. We compare the performance of three different scaled modeling units: context dependent phoneme(CDP), syllable with tone and Chinese character. We find that all types of modeling units can achieve approximate character error rate (CER) in CTC model and the performance of Chinese character attention model is better than syllable attention model. Furthermore, we find that Chinese character is a reasonable unit for mandarin speech recognition. On DidiCallcenter task, Chinese character attention model achieves a CER of 5.68% and CTC model gets a CER of 7.29%, on the other DidiReading task, CER are 4.89% and 5.79%, respectively. Moreover, attention model achieves a better performance than CTC model on both datasets.

arXiv:1709.00505

ShapeCodes: Self-Supervised Feature Learning by Lifting Views to Viewgrids

We introduce an unsupervised feature learning approach that embeds 3D shape information into a single-view image representation. The main idea is a self-supervised training objective that, given only a single 2D image, requires all unseen views of the object to be predictable from learned features. We implement this idea as an encoder-decoder convolutional neural network. The network maps an input image of an unknown category and unknown viewpoint to a latent space, from which a deconvolutional decoder can best "lift" the image to its complete viewgrid showing the object from all viewing angles. Our class-agnostic training procedure encourages the representation to capture fundamental shape primitives and semantic regularities in a data-driven manner---without manual semantic labels. Our results on two widely-used shape datasets show 1) our approach successfully learns to perform "mental rotation" even for objects unseen during training, and 2) the learned latent space is a powerful representation for object recognition, outperforming several existing unsupervised feature learning methods.

arXiv:1805.06130

Towards Robust Neural Machine Translation

Small perturbations in the input can severely distort intermediate representations and thus impact translation quality of neural machine translation (NMT) models. In this paper, we propose to improve the robustness of NMT models with adversarial stability training. The basic idea is to make both the encoder and decoder in NMT models robust against input perturbations by enabling them to behave similarly for the original input and its perturbed counterpart. Experimental results on Chinese-English, English-German and English-French translation tasks show that our approaches can not only achieve significant improvements over strong NMT systems but also improve the robustness of NMT models.

arXiv:1805.06939

Event2Mind: Commonsense Inference on Events, Intents, and Reactions

We investigate a new commonsense inference task: given an event described in a short free-form text ("X drinks coffee in the morning"), a system reasons about the likely intents ("X wants to stay awake") and reactions ("X feels alert") of the event's participants. To support this study, we construct a new crowdsourced corpus of 25,000 event phrases covering a diverse range of everyday events and situations. We report baseline performance on this task, demonstrating that neural encoder-decoder models can successfully compose embedding representations of previously unseen events and reason about the likely intents and reactions of the event participants. In addition, we demonstrate how commonsense inference on people's intents and reactions can help unveil the implicit gender inequality prevalent in modern movie scripts.

arXiv:1805.06725공식 코드 · Papers with Code

GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training

Anomaly detection is a classical problem in computer vision, namely the determination of the normal from the abnormal when datasets are highly biased towards one class (normal) due to the insufficient sample size of the other class (abnormal). While this can be addressed as a supervised learning problem, a significantly more challenging problem is that of detecting the unknown/unseen anomaly case that takes us instead into the space of a one-class, semi-supervised learning paradigm. We introduce such a novel anomaly detection model, by using a conditional generative adversarial network that jointly learns the generation of high-dimensional image space and the inference of latent space. Employing encoder-decoder-encoder sub-networks in the generator network enables the model to map the input image to a lower dimension vector, which is then used to reconstruct the generated output image. The use of the additional encoder network maps this generated image to its latent representation. Minimizing the distance between these images and the latent vectors during training aids in learning the data distribution for the normal samples. As a result, a larger distance metric from this learned data distribution at inference time is indicative of an outlier from that distribution - an anomaly. Experimentation over several benchmark datasets, from varying domains, shows the model efficacy and superiority over previous state-of-the-art approaches.

arXiv:1805.07429

Designing communication systems via iterative improvement: error correction coding with Bayes decoder and codebook optimized for source symbol error

In most error correction coding (ECC) frameworks, the typical error metric is the bit error rate (BER) which measures the number of bit errors. For this metric, the positions of the bits are not relevant to the decoding, and in many noise models, not relevant to the BER either. In many applications this is unsatisfactory as typically all bits are not equal and have different significance. We consider the problem of bit error correction and mitigation where bits in different positions have different importance. For error correction, we look at ECC from a Bayesian perspective and introduce Bayes estimators with general loss functions to take into account the bit significance. We propose ECC schemes that optimize this error metric. As the problem is highly nonlinear, traditional ECC construction techniques are not applicable. Using exhaustive search is cost prohibitive, and thus we use iterative improvement search techniques to find good codebooks. We optimize both general codebooks and linear codes. We provide numerical experiments to show that they can be superior to classical linear block codes such as Hamming codes and decoding methods such as minimum distance decoding. For error mitigation, we study the case where ECC is not possible or not desirable, but significance aware encoding of information is still beneficial in reducing the average error. We propose a novel number presentation format suitable for emerging storage media where the noise magnitude is unknown and possibly large and show that it has lower mean error than the traditional number format.

arXiv:1805.07112

Improving Image Captioning with Conditional Generative Adversarial Nets

In this paper, we propose a novel conditional-generative-adversarial-nets-based image captioning framework as an extension of traditional reinforcement-learning (RL)-based encoder-decoder architecture. To deal with the inconsistent evaluation problem among different objective language metrics, we are motivated to design some "discriminator" networks to automatically and progressively determine whether generated caption is human described or machine generated. Two kinds of discriminator architectures (CNN and RNN-based structures) are introduced since each has its own advantages. The proposed algorithm is generic so that it can enhance any existing RL-based image captioning framework and we show that the conventional RL training method is just a special case of our approach. Empirically, we show consistent improvements over all language evaluation metrics for different state-of-the-art image captioning models. In addition, the well-trained discriminators can also be viewed as objective image captioning evaluators

arXiv:1805.06239

A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese

The choice of modeling units is critical to automatic speech recognition (ASR) tasks. Conventional ASR systems typically choose context-dependent states (CD-states) or context-dependent phonemes (CD-phonemes) as their modeling units. However, it has been challenged by sequence-to-sequence attention-based models, which integrate an acoustic, pronunciation and language model into a single neural network. On English ASR tasks, previous attempts have already shown that the modeling unit of graphemes can outperform that of phonemes by sequence-to-sequence attention-based model. In this paper, we are concerned with modeling units on Mandarin Chinese ASR tasks using sequence-to-sequence attention-based models with the Transformer. Five modeling units are explored including context-independent phonemes (CI-phonemes), syllables, words, sub-words and characters. Experiments on HKUST datasets demonstrate that the lexicon free modeling units can outperform lexicon related modeling units in terms of character error rate (CER). Among five modeling units, character based model performs best and establishes a new state-of-the-art CER of $26.64\%$ on HKUST datasets without a hand-designed lexicon and an extra language model integration, which corresponds to a $4.8\%$ relative improvement over the existing best CER of $28.0\%$ by the joint CTC-attention based encoder-decoder network.

arXiv:1805.07653

Learning a face space for experiments on human identity

Generative models of human identity and appearance have broad applicability to behavioral science and technology, but the exquisite sensitivity of human face perception means that their utility hinges on the alignment of the model's representation to human psychological representations and the photorealism of the generated images. Meeting these requirements is an exacting task, and existing models of human identity and appearance are often unworkably abstract, artificial, uncanny, or biased. Here, we use a variational autoencoder with an autoregressive decoder to learn a face space from a uniquely diverse dataset of portraits that control much of the variation irrelevant to human identity and appearance. Our method generates photorealistic portraits of fictive identities with a smooth, navigable latent space. We validate our model's alignment with human sensitivities by introducing a psychophysical Turing test for images, which humans mostly fail. Lastly, we demonstrate an initial application of our model to the problem of fast search in mental space to obtain detailed "police sketches" in a small number of trials.

arXiv:1805.08191

Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation

We propose a hierarchically structured reinforcement learning approach to address the challenges of planning for generating coherent multi-sentence stories for the visual storytelling task. Within our framework, the task of generating a story given a sequence of images is divided across a two-level hierarchical decoder. The high-level decoder constructs a plan by generating a semantic concept (i.e., topic) for each image in sequence. The low-level decoder generates a sentence for each image using a semantic compositional network, which effectively grounds the sentence generation conditioned on the topic. The two decoders are jointly trained end-to-end using reinforcement learning. We evaluate our model on the visual storytelling (VIST) dataset. Empirical results from both automatic and human evaluations demonstrate that the proposed hierarchically structured reinforced training achieves significantly better performance compared to a strong flat deep reinforcement learning baseline.

arXiv:1805.08097

Invariant Representations from Adversarially Censored Autoencoders

We combine conditional variational autoencoders (VAE) with adversarial censoring in order to learn invariant representations that are disentangled from nuisance/sensitive variations. In this method, an adversarial network attempts to recover the nuisance variable from the representation, which the VAE is trained to prevent. Conditioning the decoder on the nuisance variable enables clean separation of the representation, since they are recombined for model learning and data reconstruction. We show this natural approach is theoretically well-founded with information-theoretic arguments. Experiments demonstrate that this method achieves invariance while preserving model learning performance, and results in visually improved performance for style transfer and generative sampling tasks.

arXiv:1805.07946공식 코드 · Papers with Code

Morphological analysis using a sequence decoder

We introduce Morse, a recurrent encoder-decoder model that produces morphological analyses of each word in a sentence. The encoder turns the relevant information about the word and its context into a fixed size vector representation and the decoder generates the sequence of characters for the lemma followed by a sequence of individual morphological features. We show that generating morphological features individually rather than as a combined tag allows the model to handle rare or unseen tags and outperform whole-tag models. In addition, generating morphological features as a sequence rather than e.g.\ an unordered set allows our model to produce an arbitrary number of features that represent multiple inflectional groups in morphologically complex languages. We obtain state-of-the art results in nine languages of different morphological complexity under low-resource, high-resource and transfer learning settings. We also introduce TrMor2018, a new high accuracy Turkish morphology dataset. Our Morse implementation and the TrMor2018 dataset are available online to support future research\footnote{See \url{https://github.com/ai-ku/Morse.jl} for a Morse implementation in Julia/Knet \cite{knet2016mlsys} and \url{https://github.com/ai-ku/TrMor2018} for the new Turkish dataset.}.

arXiv:1801.09030

Exploration on Generating Traditional Chinese Medicine Prescription from Symptoms with an End-to-End method

Traditional Chinese Medicine (TCM) is an influential form of medical treatment in China and surrounding areas. In this paper, we propose a TCM prescription generation task that aims to automatically generate a herbal medicine prescription based on textual symptom descriptions. Sequence-to-sequence (seq2seq) model has been successful in dealing with sequence generation tasks. We explore a potential end-to-end solution to the TCM prescription generation task using seq2seq models. However, experiments show that directly applying seq2seq model leads to unfruitful results due to the repetition problem. To solve the problem, we propose a novel decoder with coverage mechanism and a novel soft loss function. The experimental results demonstrate the effectiveness of the proposed approach. Judged by professors who excel in TCM, the generated prescriptions are rated 7.3 out of 10. It shows that the model can indeed help with the prescribing procedure in real life.

arXiv:1801.05463

Deep learning for determining a near-optimal topological design without any iteration

In this study, we propose a novel deep learning-based method to predict an optimized structure for a given boundary condition and optimization setting without using any iterative scheme. For this purpose, first, using open-source topology optimization code, datasets of the optimized structures paired with the corresponding information on boundary conditions and optimization settings are generated at low (32 x 32) and high (128 x 128) resolutions. To construct the artificial neural network for the proposed method, a convolutional neural network (CNN)-based encoder and decoder network is trained using the training dataset generated at low resolution. Then, as a two-stage refinement, the conditional generative adversarial network (cGAN) is trained with the optimized structures paired at both low and high resolutions, and is connected to the trained CNN-based encoder and decoder network. The performance evaluation results of the integrated network demonstrate that the proposed method can determine a near-optimal structure in terms of pixel values and compliance with negligible computational time.

arXiv:1712.02051공식 코드 · Papers with Code

Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning

Visual language grounding is widely studied in modern neural image captioning systems, which typically adopts an encoder-decoder framework consisting of two principal components: a convolutional neural network (CNN) for image feature extraction and a recurrent neural network (RNN) for language caption generation. To study the robustness of language grounding to adversarial perturbations in machine vision and perception, we propose Show-and-Fool, a novel algorithm for crafting adversarial examples in neural image captioning. The proposed algorithm provides two evaluation approaches, which check whether neural image captioning systems can be mislead to output some randomly chosen captions or keywords. Our extensive experiments show that our algorithm can successfully craft visually-similar adversarial examples with randomly targeted captions or keywords, and the adversarial examples can be made highly transferable to other image captioning systems. Consequently, our approach leads to new robustness implications of neural image captioning and novel insights in visual language grounding.

arXiv:1804.05685공식 코드 · Papers with Code

A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents

Neural abstractive summarization models have led to promising results in summarizing relatively short documents. We propose the first model for abstractive summarization of single, longer-form documents (e.g., research papers). Our approach consists of a new hierarchical encoder that models the discourse structure of a document, and an attentive discourse-aware decoder to generate the summary. Empirical results on two large-scale datasets of scientific papers show that our model significantly outperforms state-of-the-art models.

arXiv:1805.09213

Learning latent variable structured prediction models with Gaussian perturbations

The standard margin-based structured prediction commonly uses a maximum loss over all possible structured outputs. The large-margin formulation including latent variables not only results in a non-convex formulation but also increases the search space by a factor of the size of the latent space. Recent work has proposed the use of the maximum loss over random structured outputs sampled independently from some proposal distribution, with theoretical guarantees. We extend this work by including latent variables. We study a new family of loss functions under Gaussian perturbations and analyze the effect of the latent space on the generalization bounds. We show that the non-convexity of learning with latent variables originates naturally, as it relates to a tight upper bound of the Gibbs decoder distortion with respect to the latent space. Finally, we provide a formulation using random samples that produces a tighter upper bound of the Gibbs decoder distortion up to a statistical accuracy, which enables a faster evaluation of the objective function. We illustrate the method with synthetic experiments and a computer vision application.