With the recent success of the pre-training technique for NLP and image-linguistic tasks, some video-linguistic pre-training works are gradually developed to improve video-text related downstream tasks. However, most of the existing multimodal models are pre-trained for understanding tasks, leading to a pretrain-finetune discrepancy for generation tasks. This paper proposes UniVL: a Unified Video and Language pre-training model for both multimodal understanding and generation. It comprises four components, including two single-modal encoders, a cross encoder, and a decoder with the Transformer backbone. Five objectives, including video-text joint, conditioned masked language model (CMLM), conditioned masked frame model (CMFM), video-text alignment, and language reconstruction, are designed to train each of the components. We further develop two pre-training strategies, stage by stage pre-training (StagedP) and enhanced video representation (EnhancedV), to make the training process of the UniVL more effective. The pre-train is carried out on a sizeable instructional video dataset HowTo100M. Experimental results demonstrate that the UniVL can learn strong video-text representation and achieves state-of-the-art results on five downstream tasks.
Automatic map extraction is of great importance to urban computing and location-based services. Aerial image and GPS trajectory data refer to two different data sources that could be leveraged to generate the map, although they carry different types of information. Most previous works on data fusion between aerial images and data from auxiliary sensors do not fully utilize the information of both modalities and hence suffer from the issue of information loss. We propose a deep convolutional neural network called DeepDualMapper which fuses the aerial image and trajectory data in a more seamless manner to extract the digital map. We design a gated fusion module to explicitly control the information flows from both modalities in a complementary-aware manner. Moreover, we propose a novel densely supervised refinement decoder to generate the prediction in a coarse-to-fine way. Our comprehensive experiments demonstrate that DeepDualMapper can fuse the information of images and trajectories much more effectively than existing approaches, and is able to generate maps with higher accuracy.
The recently proposed BERT has shown great power on a variety of natural language understanding tasks, such as text classification, reading comprehension, etc. However, how to effectively apply BERT to neural machine translation (NMT) lacks enough exploration. While BERT is more commonly used as fine-tuning instead of contextual embedding for downstream language understanding tasks, in NMT, our preliminary exploration of using BERT as contextual embedding is better than using for fine-tuning. This motivates us to think how to better leverage BERT for NMT along this direction. We propose a new algorithm named BERT-fused model, in which we first use BERT to extract representations for an input sequence, and then the representations are fused with each layer of the encoder and decoder of the NMT model through attention mechanisms. We conduct experiments on supervised (including sentence-level and document-level translations), semi-supervised and unsupervised machine translation, and achieve state-of-the-art results on seven benchmark datasets. Our code is available at \url{https://github.com/bert-nmt/bert-nmt}.
In this paper our goal is to convert a set of spoken lines into sung ones. Unlike previous signal processing based methods, we take a learning based approach to the problem. This allows us to automatically model various aspects of this transformation, thus overcoming dependence on specific inputs such as high quality singing templates or phoneme-score synchronization information. Specifically, we propose an encoder--decoder framework for our task. Given time-frequency representations of speech and a target melody contour, we learn encodings that enable us to synthesize singing that preserves the linguistic content and timbre of the speaker while adhering to the target melody. We also propose a multi-task learning based objective to improve lyric intelligibility. We present a quantitative and qualitative analysis of our framework.
Though early successes of Statistical Machine Translation (SMT) systems are attributed in part to the explicit modelling of the interaction between any two source and target units, e.g., alignment, the recent Neural Machine Translation (NMT) systems resort to the attention which partially encodes the interaction for efficiency. In this paper, we employ Joint Representation that fully accounts for each possible interaction. We sidestep the inefficiency issue by refining representations with the proposed efficient attention operation. The resulting Reformer models offer a new Sequence-to- Sequence modelling paradigm besides the Encoder-Decoder framework and outperform the Transformer baseline in either the small scale IWSLT14 German-English, English-German and IWSLT15 Vietnamese-English or the large scale NIST12 Chinese-English translation tasks by about 1 BLEU point.We also propose a systematic model scaling approach, allowing the Reformer model to beat the state-of-the-art Transformer in IWSLT14 German-English and NIST12 Chinese-English with about 50% fewer parameters. The code is publicly available at https://github.com/lyy1994/reformer.
Semantic parsing is the task of obtaining machine-interpretable representations from natural language text. We consider one such formal representation - First-Order Logic (FOL) and explore the capability of neural models in parsing English sentences to FOL. We model FOL parsing as a sequence to sequence mapping task where given a natural language sentence, it is encoded into an intermediate representation using an LSTM followed by a decoder which sequentially generates the predicates in the corresponding FOL formula. We improve the standard encoder-decoder model by introducing a variable alignment mechanism that enables it to align variables across predicates in the predicted FOL. We further show the effectiveness of predicting the category of FOL entity - Unary, Binary, Variables and Scoped Entities, at each decoder step as an auxiliary task on improving the consistency of generated FOL. We perform rigorous evaluations and extensive ablations. We also aim to release our code as well as large scale FOL dataset along with models to aid further research in logic-based parsing and inference in NLP.
We propose an unsupervised speaker adaptation method inspired by the neural Turing machine for end-to-end (E2E) automatic speech recognition (ASR). The proposed model contains a memory block that holds speaker i-vectors extracted from the training data and reads relevant i-vectors from the memory through an attention mechanism. The resulting memory vector (M-vector) is concatenated to the acoustic features or to the hidden layer activations of an E2E neural network model. The E2E ASR system is based on the joint connectionist temporal classification and attention-based encoder-decoder architecture. M-vector and i-vector results are compared for inserting them at different layers of the encoder neural network using the WSJ and TED-LIUM2 ASR benchmarks. We show that M-vectors, which do not require an auxiliary speaker embedding extraction system at test time, achieve similar word error rates (WERs) compared to i-vectors for single speaker utterances and significantly lower WERs for utterances in which there are speaker changes.
Using the raw data from consumer-level RGB-D cameras as input, we propose a deep-learning based approach to efficiently generate RGB-D images with completed information in high resolution. To process the input images in low resolution with missing regions, new operators for adaptive convolution are introduced in our deep-learning network that consists of three cascaded modules -- the completion module, the refinement module and the super-resolution module. The completion module is based on an architecture of encoder-decoder, where the features of input raw RGB-D will be automatically extracted by the encoding layers of a deep neural-network. The decoding layers are applied to reconstruct the completed depth map, which is followed by a refinement module to sharpen the boundary of different regions. For the super-resolution module, we generate RGB-D images in high resolution by multiple layers for feature extraction and a layer for up-sampling. Benefited from the adaptive convolution operators newly proposed in this paper, our results outperform the existing deep-learning based approaches for RGB-D image complete and super-resolution. As an end-to-end approach, high fidelity RGB-D images can be generated efficiently at the rate of around 21 frames per second.
Multi-vehicle routing problem with soft time windows (MVRPSTW) is an indispensable constituent in urban logistics distribution systems. Over the past decade, numerous methods for MVRPSTW have been proposed, but most are based on heuristic rules that require a large amount of computation time. With the current rapid increase of logistics demands, traditional methods incur the dilemma between computational efficiency and solution quality. To efficiently solve the problem, we propose a novel reinforcement learning algorithm called the Multi-Agent Attention Model that can solve routing problem instantly benefit from lengthy offline training. Specifically, the vehicle routing problem is regarded as a vehicle tour generation process, and an encoder-decoder framework with attention layers is proposed to generate tours of multiple vehicles iteratively. Furthermore, a multi-agent reinforcement learning method with an unsupervised auxiliary network is developed for the model training. By evaluated on four synthetic networks with different scales, the results demonstrate that the proposed method consistently outperforms Google OR-Tools and traditional methods with little computation time. In addition, we validate the robustness of the well-trained model by varying the number of customers and the capacities of vehicles.
Deep Learning (DL) techniques for Natural Language Processing have been evolving remarkably fast. Recently, the DL advances in language modeling, machine translation and paragraph understanding are so prominent that the potential of DL in Software Engineering cannot be overlooked, especially in the field of program learning. To facilitate further research and applications of DL in this field, we provide a comprehensive review to categorize and investigate existing DL methods for source code modeling and generation. To address the limitations of the traditional source code models, we formulate common program learning tasks under an encoder-decoder framework. After that, we introduce recent DL mechanisms suitable to solve such problems. Then, we present the state-of-the-art practices and discuss their challenges with some recommendations for practitioners and researchers as well.
We present a deep learning based methodology for extracting the singing voice signal from a musical mixture based on the underlying linguistic content. Our model follows an encoder decoder architecture and takes as input the magnitude component of the spectrogram of a musical mixture with vocals. The encoder part of the model is trained via knowledge distillation using a teacher network to learn a content embedding, which is decoded to generate the corresponding vocoder features. Using this methodology, we are able to extract the unprocessed raw vocal signal from the mixture even for a processed mixture dataset with singers not seen during training. While the nature of our system makes it incongruous with traditional objective evaluation metrics, we use subjective evaluation via listening tests to compare the methodology to state-of-the-art deep learning based source separation algorithms. We also provide sound examples and source code for reproducibility.
Measuring the similarity between data points often requires domain knowledge, which can in parts be compensated by relying on unsupervised methods such as latent-variable models, where similarity/distance is estimated in a more compact latent space. Prevalent is the use of the Euclidean metric, which has the drawback of ignoring information about similarity of data stored in the decoder, as captured by the framework of Riemannian geometry. We propose an extension to the framework of variational auto-encoders allows learning flat latent manifolds, where the Euclidean metric is a proxy for the similarity between data points. This is achieved by defining the latent space as a Riemannian manifold and by regularising the metric tensor to be a scaled identity matrix. Additionally, we replace the compact prior typically used in variational auto-encoders with a recently presented, more expressive hierarchical one---and formulate the learning problem as a constrained optimisation problem. We evaluate our method on a range of data-sets, including a video-tracking benchmark, where the performance of our unsupervised approach nears that of state-of-the-art supervised approaches, while retaining the computational efficiency of straight-line-based approaches.
Mutation testing can be used to assess the fault-detection capabilities of a given test suite. To this aim, two characteristics of mutation testing frameworks are of paramount importance: (i) they should generate mutants that are representative of real faults; and (ii) they should provide a complete tool chain able to automatically generate, inject, and test the mutants. To address the first point, we recently proposed an approach using a Recurrent Neural Network Encoder-Decoder architecture to learn mutants from ~787k faults mined from real programs. The empirical evaluation of this approach confirmed its ability to generate mutants representative of real faults. In this paper, we address the second point, presenting DeepMutation, a tool wrapping our deep learning model into a fully automated tool chain able to generate, inject, and test mutants learned from real faults. Video: https://sites.google.com/view/learning-mutation/deepmutation
We discuss the problem of echographic transcription in autoregressive sequence-to-sequence attentional architectures for automatic speech recognition, where a model produces very long sequences of repetitive outputs when presented with out-of-domain utterances. We decode audio from the British National Corpus with an attentional encoder-decoder model trained solely on the LibriSpeech corpus. We observe that there are many 5-second recordings that produce more than 500 characters of decoding output (i.e. more than 100 characters per second). A frame-synchronous hybrid (DNN-HMM) model trained on the same data does not produce these unusually long transcripts. These decoding issues are reproducible in a speech transformer model from ESPnet, and to a lesser extent in a self-attention CTC model, suggesting that these issues are intrinsic to the use of the attention mechanism. We create a separate length prediction model to predict the correct number of wordpieces in the output, which allows us to identify and truncate problematic decoding results without increasing word error rates on the LibriSpeech task.
We propose a statistical learning-based traffic speed estimation method that uses sparse vehicle trajectory information. Using a convolutional encoder-decoder based architecture, we show that a well trained neural network can learn spatio-temporal traffic speed dynamics from time-space diagrams. We demonstrate this for a homogeneous road section using simulated vehicle trajectories and then validate it using real-world data from NGSIM. Our results show that with probe vehicle penetration levels as low as 5\%, the proposed estimation method can provide a sound reconstruction of macroscopic traffic speeds and reproduce realistic shockwave patterns, implying applicability in a variety of traffic conditions. We further discuss the model's reconstruction mechanisms and confirm its ability to differentiate various traffic behaviors such as congested and free-flow traffic states, transition dynamics, and shockwave propagation.
Textures and edges contribute different information to image recognition. Edges and boundaries encode shape information, while textures manifest the appearance of regions. Despite the success of Convolutional Neural Networks (CNNs) in computer vision and medical image analysis applications, predominantly only texture abstractions are learned, which often leads to imprecise boundary delineations. In medical imaging, expert manual segmentation often relies on organ boundaries; for example, to manually segment a liver, a medical practitioner usually identifies edges first and subsequently fills in the segmentation mask. Motivated by these observations, we propose a plug-and-play module, dubbed Edge-Gated CNNs (EG-CNNs), that can be used with existing encoder-decoder architectures to process both edge and texture information. The EG-CNN learns to emphasize the edges in the encoder, to predict crisp boundaries by an auxiliary edge supervision, and to fuse its output with the original CNN output. We evaluate the effectiveness of the EG-CNN with various mainstream CNNs on two publicly available datasets, BraTS 19 and KiTS 19 for brain tumor and kidney semantic segmentation. We demonstrate how the addition of EG-CNN consistently improves segmentation accuracy and generalization performance.
Non-autoregressive translation (NAT) models generate multiple tokens in one forward pass and is highly efficient at inference stage compared with autoregressive translation (AT) methods. However, NAT models often suffer from the multimodality problem, i.e., generating duplicated tokens or missing tokens. In this paper, we propose two novel methods to address this issue, the Look-Around (LA) strategy and the Vocabulary Attention (VA) mechanism. The Look-Around strategy predicts the neighbor tokens in order to predict the current token, and the Vocabulary Attention models long-term token dependencies inside the decoder by attending the whole vocabulary for each position to acquire knowledge of which token is about to generate. %We also propose a dynamic bidirectional decoding approach to accelerate the inference process of the LAVA model while preserving the high-quality of the generated output. Our proposed model uses significantly less time during inference compared with autoregressive models and most other NAT models. Our experiments on four benchmarks (WMT14 En$\rightarrow$De, WMT14 De$\rightarrow$En, WMT16 Ro$\rightarrow$En and IWSLT14 De$\rightarrow$En) show that the proposed model achieves competitive performance compared with the state-of-the-art non-autoregressive and autoregressive models while significantly reducing the time cost in inference phase.
In many professional fields, such as medicine, remote sensing and sciences, users often demand image compression methods to be mathematically lossless. But lossless image coding has a rather low compression ratio (around 2:1 for natural images). The only known technique to achieve significant compression while meeting the stringent fidelity requirements is the methodology of $\ell_\infty$-constrained coding that was developed and standardized in nineties. We make a major progress in $\ell_\infty$-constrained image coding after two decades, by developing a novel CNN-based soft $\ell_\infty$-constrained decoding method. The new method repairs compression defects by using a restoration CNN called the $\ell_\infty\mbox{-SDNet}$ to map a conventionally decoded image to the latent image. A unique strength of the $\ell_\infty\mbox{-SDNet}$ is its ability to enforce a tight error bound on a per pixel basis. As such, no small distinctive structures of the original image can be dropped or distorted, even if they are statistical outliers that are otherwise sacrificed by mainstream CNN restoration methods. More importantly, this research ushers in a new image compression system of $\ell_\infty$-constrained encoding and deep soft decoding ($\ell_\infty\mbox{-ED}^2$). The $\ell_\infty \mbox{-ED}^2$ approach beats the best of existing lossy image compression methods (e.g., BPG, WebP, etc.) not only in $\ell_\infty$ but also in $\ell_2$ error metric and perceptual quality, for bit rates near the threshold of perceptually transparent reconstruction. Operationally, the new compression system is practical, with a low-complexity real-time encoder and a cascade decoder consisting of a fast initial decoder and an optional CNN soft decoder.
Image compression is a widely used technique to reduce the spatial redundancy in images. Recently, learning based image compression has achieved significant progress by using the powerful representation ability from neural networks. However, the current state-of-the-art learning based image compression methods suffer from the huge computational cost, which limits their capacity for practical applications. In this paper, we propose a unified framework called Efficient Deep Image Compression (EDIC) based on three new technologies, including a channel attention module, a Gaussian mixture model and a decoder-side enhancement module. Specifically, we design an auto-encoder style network for learning based image compression. To improve the coding efficiency, we exploit the channel relationship between latent representations by using the channel attention module. Besides, the Gaussian mixture model is introduced for the entropy model and improves the accuracy for bitrate estimation. Furthermore, we introduce the decoder-side enhancement module to further improve image compression performance. Our EDIC method can also be readily incorporated with the Deep Video Compression (DVC) framework to further improve the video compression performance. Simultaneously, our EDIC method boosts the coding performance significantly while bringing slightly increased computational cost. More importantly, experimental results demonstrate that the proposed approach outperforms the current state-of-the-art image compression methods and is up to more than 150 times faster in terms of decoding speed when compared with Minnen's method. The proposed framework also successfully improves the performance of the recent deep video compression system DVC. Our code will be released at https://github.com/liujiaheng/compression.
Recent researches show that machine learning has the potential to learn better heuristics than the one designed by human for solving combinatorial optimization problems. The deep neural network is used to characterize the input instance for constructing a feasible solution incrementally. Recently, an attention model is proposed to solve routing problems. In this model, the state of an instance is represented by node features that are fixed over time. However, the fact is, the state of an instance is changed according to the decision that the model made at different construction steps, and the node features should be updated correspondingly. Therefore, this paper presents a dynamic attention model with dynamic encoder-decoder architecture, which enables the model to explore node features dynamically and exploit hidden structure information effectively at different construction steps. This paper focuses on a challenging NP-hard problem, vehicle routing problem. The experiments indicate that our model outperforms the previous methods and also shows a good generalization performance.