Human interactions and human-computer interactions are strongly influenced by style as well as content. Adding a persona to a chatbot makes it more human-like and contributes to a better and more engaging user experience. In this work, we propose a design for a chatbot that captures the "style" of Star Trek by incorporating references from the show along with peculiar tones of the fictional characters therein. Our Enterprise to Computer bot (E2Cbot) treats Star Trek dialog style and general dialog style differently, using two recurrent neural network Encoder-Decoder models. The Star Trek dialog style uses sequence to sequence (SEQ2SEQ) models (Sutskever et al., 2014; Bahdanau et al., 2014) trained on Star Trek dialogs. The general dialog style uses Word Graph to shift the response of the SEQ2SEQ model into the Star Trek domain. We evaluate the bot both in terms of perplexity and word overlap with Star Trek vocabulary and subjectively using human evaluators.
In the encoder-decoder architecture for neural machine translation (NMT), the hidden states of the recurrent structures in the encoder and decoder carry the crucial information about the sentence.These vectors are generated by parameters which are updated by back-propagation of translation errors through time. We argue that propagating errors through the end-to-end recurrent structures are not a direct way of control the hidden vectors. In this paper, we propose to use word predictions as a mechanism for direct supervision. More specifically, we require these vectors to be able to predict the vocabulary in target sentence. Our simple mechanism ensures better representations in the encoder and decoder without using any extra data or annotation. It is also helpful in reducing the target side vocabulary and improving the decoding efficiency. Experiments on Chinese-English and German-English machine translation tasks show BLEU improvements by 4.53 and 1.3, respectively
Grapheme-to-phoneme conversion (g2p) is necessary for text-to-speech and automatic speech recognition systems. Most g2p systems are monolingual: they require language-specific data or handcrafting of rules. Such systems are difficult to extend to low resource languages, for which data and handcrafted rules are not available. As an alternative, we present a neural sequence-to-sequence approach to g2p which is trained on spelling--pronunciation pairs in hundreds of languages. The system shares a single encoder and decoder across all languages, allowing it to utilize the intrinsic similarities between different writing systems. We show an 11% improvement in phoneme error rate over an approach based on adapting high-resource monolingual g2p models to low-resource languages. Our model is also much more compact relative to previous approaches.
Photorealistic frontal view synthesis from a single face image has a wide range of applications in the field of face recognition. Although data-driven deep learning methods have been proposed to address this problem by seeking solutions from ample face data, this problem is still challenging because it is intrinsically ill-posed. This paper proposes a Two-Pathway Generative Adversarial Network (TP-GAN) for photorealistic frontal view synthesis by simultaneously perceiving global structures and local details. Four landmark located patch networks are proposed to attend to local textures in addition to the commonly used global encoder-decoder network. Except for the novel architecture, we make this ill-posed problem well constrained by introducing a combination of adversarial loss, symmetry loss and identity preserving loss. The combined loss function leverages both frontal face distribution and pre-trained discriminative deep face models to guide an identity preserving inference of frontal views from profiles. Different from previous deep learning methods that mainly rely on intermediate features for recognition, our method directly leverages the synthesized identity preserving image for downstream tasks like face recognition and attribution estimation. Experimental results demonstrate that our method not only presents compelling perceptual results but also outperforms state-of-the-art results on large pose face recognition.
In this paper, we propose a secure multibiometric system that uses deep neural networks and error-correction coding. We present a feature-level fusion framework to generate a secure multibiometric template from each user's multiple biometrics. Two fusion architectures, fully connected architecture and bilinear architecture, are implemented to develop a robust multibiometric shared representation. The shared representation is used to generate a cancelable biometric template that involves the selection of a different set of reliable and discriminative features for each user. This cancelable template is a binary vector and is passed through an appropriate error-correcting decoder to find a closest codeword and this codeword is hashed to generate the final secure template. The efficacy of the proposed approach is shown using a multimodal database where we achieve state-of-the-art matching performance, along with cancelability and security.
Deep convolutional neural networks (CNNs) have delivered superior performance in many computer vision tasks. In this paper, we propose a novel deep fully convolutional network model for accurate salient object detection. The key contribution of this work is to learn deep uncertain convolutional features (UCF), which encourage the robustness and accuracy of saliency detection. We achieve this via introducing a reformulated dropout (R-dropout) after specific convolutional layers to construct an uncertain ensemble of internal feature units. In addition, we propose an effective hybrid upsampling method to reduce the checkerboard artifacts of deconvolution operators in our decoder network. The proposed methods can also be applied to other deep convolutional networks. Compared with existing saliency detection methods, the proposed UCF model is able to incorporate uncertainties for more accurate object boundary inference. Extensive experiments demonstrate that our proposed saliency model performs favorably against state-of-the-art approaches. The uncertain feature learning mechanism as well as the upsampling method can significantly improve performance on other pixel-wise vision tasks.
Phrases play an important role in natural language understanding and machine translation (Sag et al., 2002; Villavicencio et al., 2005). However, it is difficult to integrate them into current neural machine translation (NMT) which reads and generates sentences word by word. In this work, we propose a method to translate phrases in NMT by integrating a phrase memory storing target phrases from a phrase-based statistical machine translation (SMT) system into the encoder-decoder architecture of NMT. At each decoding step, the phrase memory is first re-written by the SMT model, which dynamically generates relevant target phrases with contextual information provided by the NMT model. Then the proposed model reads the phrase memory to make probability estimations for all phrases in the phrase memory. If phrase generation is carried on, the NMT decoder selects an appropriate phrase from the memory to perform phrase translation and updates its decoding state by consuming the words in the selected phrase. Otherwise, the NMT decoder generates a word from the vocabulary as the general NMT decoder does. Experiment results on the Chinese to English translation show that the proposed model achieves significant improvements over the baseline on various test sets.
We present a deep convolutional decoder architecture that can generate volumetric 3D outputs in a compute- and memory-efficient manner by using an octree representation. The network learns to predict both the structure of the octree, and the occupancy values of individual cells. This makes it a particularly valuable technique for generating 3D shapes. In contrast to standard decoders acting on regular voxel grids, the architecture does not have cubic complexity. This allows representing much higher resolution outputs with a limited memory budget. We demonstrate this in several application domains, including 3D convolutional autoencoders, generation of objects and whole scenes from high-level representations, and shape from a single image.
This paper focuses on the task of room layout estimation from a monocular RGB image. Prior works break the problem into two sub-tasks: semantic segmentation of floor, walls, ceiling to produce layout hypotheses, followed by an iterative optimization step to rank these hypotheses. In contrast, we adopt a more direct formulation of this problem as one of estimating an ordered set of room layout keypoints. The room layout and the corresponding segmentation is completely specified given the locations of these ordered keypoints. We predict the locations of the room layout keypoints using RoomNet, an end-to-end trainable encoder-decoder network. On the challenging benchmark datasets Hedau and LSUN, we achieve state-of-the-art performance along with 200x to 600x speedup compared to the most recent work. Additionally, we present optional extensions to the RoomNet architecture such as including recurrent computations and memory units to refine the keypoint locations under the same parametric capacity.
Most approaches for instance-aware semantic labeling traditionally focus on accuracy. Other aspects like runtime and memory footprint are arguably as important for real-time applications such as autonomous driving. Motivated by this observation and inspired by recent works that tackle multiple tasks with a single integrated architecture, in this paper we present a real-time efficient implementation based on ENet that solves three autonomous driving related tasks at once: semantic scene segmentation, instance segmentation and monocular depth estimation. Our approach builds upon a branched ENet architecture with a shared encoder but different decoder branches for each of the three tasks. The presented method can run at 21 fps at a resolution of 1024x512 on the Cityscapes dataset without sacrificing accuracy compared to running each task separately.
Video captioning, the task of describing the content of a video, has seen some promising improvements in recent years with sequence-to-sequence models, but accurately learning the temporal and logical dynamics involved in the task still remains a challenge, especially given the lack of sufficient annotated data. We improve video captioning by sharing knowledge with two related directed-generation tasks: a temporally-directed unsupervised video prediction task to learn richer context-aware video encoder representations, and a logically-directed language entailment generation task to learn better video-entailed caption decoder representations. For this, we present a many-to-many multi-task learning model that shares parameters across the encoders and decoders of the three tasks. We achieve significant improvements and the new state-of-the-art on several standard video captioning datasets using diverse automatic and human evaluations. We also show mutual multi-task improvements on the entailment generation task.
In this paper, we propose a novel medical image segmentation using iterative deep learning framework. We have combined an iterative learning approach and an encoder-decoder network to improve segmentation results, which enables to precisely localize the regions of interest (ROIs) including complex shapes or detailed textures of medical images in an iterative manner. The proposed iterative deep convolutional encoder-decoder network consists of two main paths: convolutional encoder path and convolutional decoder path with iterative learning. Experimental results show that the proposed iterative deep learning framework is able to yield excellent medical image segmentation performances for various medical images. The effectiveness of the proposed method has been proved by comparing with other state-of-the-art medical image segmentation methods.
Many machine vision applications, such as semantic segmentation and depth prediction, require predictions for every pixel of the input image. Models for such problems usually consist of encoders which decrease spatial resolution while learning a high-dimensional representation, followed by decoders who recover the original input resolution and result in low-dimensional predictions. While encoders have been studied rigorously, relatively few studies address the decoder side. This paper presents an extensive comparison of a variety of decoders for a variety of pixel-wise tasks ranging from classification, regression to synthesis. Our contributions are: (1) Decoders matter: we observe significant variance in results between different types of decoders on various problems. (2) We introduce new residual-like connections for decoders. (3) We introduce a novel decoder: bilinear additive upsampling. (4) We explore prediction artifacts.
Natural language generation (NLG) is a critical component in a spoken dialogue system. This paper presents a Recurrent Neural Network based Encoder-Decoder architecture, in which an LSTM-based decoder is introduced to select, aggregate semantic elements produced by an attention mechanism over the input elements, and to produce the required utterances. The proposed generator can be jointly trained both sentence planning and surface realization to produce natural language sentences. The proposed model was extensively evaluated on four different NLG datasets. The experimental results showed that the proposed generators not only consistently outperform the previous methods across all the NLG domains but also show an ability to generalize from a new, unseen domain and learn from multi-domain datasets.
Understanding the 3D world is a fundamental problem in computer vision. However, learning a good representation of 3D objects is still an open problem due to the high dimensionality of the data and many factors of variation involved. In this work, we investigate the task of single-view 3D object reconstruction from a learning agent's perspective. We formulate the learning process as an interaction between 3D and 2D representations and propose an encoder-decoder network with a novel projection loss defined by the perspective transformation. More importantly, the projection loss enables the unsupervised learning using 2D observation without explicit 3D supervision. We demonstrate the ability of the model in generating 3D volume from a single 2D image with three sets of experiments: (1) learning from single-class objects; (2) learning from multi-class objects and (3) testing on novel object classes. Results show superior performance and better generalization ability for 3D object reconstruction when the projection loss is involved.
Segmental models are an alternative to frame-based models for sequence prediction, where hypothesized path weights are based on entire segment scores rather than a single frame at a time. Neural segmental models are segmental models that use neural network-based weight functions. Neural segmental models have achieved competitive results for speech recognition, and their end-to-end training has been explored in several studies. In this work, we review neural segmental models, which can be viewed as consisting of a neural network-based acoustic encoder and a finite-state transducer decoder. We study end-to-end segmental models with different weight functions, including ones based on frame-level neural classifiers and on segmental recurrent neural networks. We study how reducing the search space size impacts performance under different weight functions. We also compare several loss functions for end-to-end training. Finally, we explore training approaches, including multi-stage vs. end-to-end training and multitask training that combines segmental and frame-level losses.
Time series account for a large proportion of the data stored in financial, medical and scientific databases. The efficient storage of time series is important in practical applications. In this paper, we propose a novel compression scheme for time series. The encoder and decoder are both composed by recurrent neural networks (RNN) such as long short-term memory (LSTM). There is an autoencoder between encoder and decoder, which encodes the hidden state and input together and decodes them at the decoder side. Moreover, we pre-process the original time series by partitioning it into segments with various lengths which have similar total variation. The experimental study shows that the proposed algorithm can achieve competitive compression ratio on real-world time series.
We propose a new deep learning approach for automatic detection and segmentation of fluid within retinal OCT images. The proposed framework utilizes both ResNet and Encoder-Decoder neural network architectures. When training the network, we apply a novel data augmentation method called myopic warping together with standard rotation-based augmentation to increase the training set size to 45 times the original amount. Finally, the network output is post-processed with an energy minimization algorithm (graph cut) along with a few other knowledge guided morphological operations to finalize the segmentation process. Based on OCT imaging data and its ground truth from the RETOUCH challenge, the proposed system achieves dice indices of 0.522, 0.682, and 0.612, and average absolute volume differences of 0.285, 0.115, and 0.156 mm$^3$ for intaretinal fluid, subretinal fluid, and pigment epithelial detachment respectively.
Image captioning often requires a large set of training image-sentence pairs. In practice, however, acquiring sufficient training pairs is always expensive, making the recent captioning models limited in their ability to describe objects outside of training corpora (i.e., novel objects). In this paper, we present Long Short-Term Memory with Copying Mechanism (LSTM-C) --- a new architecture that incorporates copying into the Convolutional Neural Networks (CNN) plus Recurrent Neural Networks (RNN) image captioning framework, for describing novel objects in captions. Specifically, freely available object recognition datasets are leveraged to develop classifiers for novel objects. Our LSTM-C then nicely integrates the standard word-by-word sentence generation by a decoder RNN with copying mechanism which may instead select words from novel objects at proper places in the output sentence. Extensive experiments are conducted on both MSCOCO image captioning and ImageNet datasets, demonstrating the ability of our proposed LSTM-C architecture to describe novel objects. Furthermore, superior results are reported when compared to state-of-the-art deep models.
Generative models defining joint distributions over parse trees and sentences are useful for parsing and language modeling, but impose restrictions on the scope of features and are often outperformed by discriminative models. We propose a framework for parsing and language modeling which marries a generative model with a discriminative recognition model in an encoder-decoder setting. We provide interpretations of the framework based on expectation maximization and variational inference, and show that it enables parsing and language modeling within a single implementation. On the English Penn Treen-bank, our framework obtains competitive performance on constituency parsing while matching the state-of-the-art single-model language modeling score.