Searcharxiv⌕ Search

arXiv subjects

Jingjing Liu

Publications and source records attributed to Jingjing Liu.

At least 163 records · Page 9Linked to original sources
arXiv2019

Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension

We propose a multi-task learning framework to learn a joint Machine Reading Comprehension (MRC) model that can be applied to a wide range of MRC tasks in different domains. Inspired by recent ideas of data selection in machine translation, we develop a novel sample re-weighting scheme to assign sample-specific weights to the loss. Empirical study shows that our approach can be applied to many existing MRC models. Combined with contextual representations from pre-trained language models (such as ELMo), we achieve new state-of-the-art results on a set of MRC benchmark datasets. We release our code at https://github.com/xycforgithub/MultiTask-MRC.

cs.CL↗
arXiv2019

Global existence and blow-up phenomena for two-component Degasperis-Procesi system and two-component b-family system

This paper is concerned with global existence and blow-up phenomena for two-component Degasperis-Procesi system and two-component b-family system. The strategy relies on our observation on new conservative quantities of these systems. Several new global existence results and a new blowup result of strong solutions to the two-component Degasperis- Procesi system and the two-component b-family system are presented by using these new conservative quantities.

math.AP↗
arXiv2018

Blow-up phenomena for the rotation-two-component Camassa-Holm system

In this paper, we study blow-up phenomena for the rotation-two-component Camassa- Holm (R2CH) system, a model of equatorial water waves that includes the effect of the Coriolis force. We first derive the precise blow-up scenario for R2CH with ? > 0: Then, we present two new blow-up results for strong solutions to the system and then the precise blow-up rate for strong solutions to the system is given.

math.AP↗
arXiv2018

Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning

Training task-completion dialogue agents with reinforcement learning usually requires a large number of real user experiences. The Dyna-Q algorithm extends Q-learning by integrating a world model, and thus can effectively boost training efficiency using simulated experiences generated by the world model. The effectiveness of Dyna-Q, however, depends on the quality of the world model - or implicitly, the pre-specified ratio of real vs. simulated experiences used for Q-learning. To this end, we extend the recently proposed Deep Dyna-Q (DDQ) framework by integrating a switcher that automatically determines whether to use a real or simulated experience for Q-learning. Furthermore, we explore the use of active learning for improving sample efficiency, by encouraging the world model to generate simulated experiences in the state-action space where the agent has not (fully) explored. Our results show that by combining switcher and active learning, the new framework named as Switch-based Active Deep Dyna-Q (Switch-DDQ), leads to significant improvement over DDQ and Q-learning baselines in both simulation and human evaluations.

cs.CL↗
arXiv2018

ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension

We present a large-scale dataset, ReCoRD, for machine reading comprehension requiring commonsense reasoning. Experiments on this dataset demonstrate that the performance of state-of-the-art MRC systems fall far behind human performance. ReCoRD represents a challenge for future research to bridge the gap between human and machine commonsense reading comprehension. ReCoRD is available at http://nlp.jhu.edu/record.

cs.CL↗
arXiv2018

A Training-based Identification Approach to VIN Adversarial Examples

With the rapid development of Artificial Intelligence (AI), the problem of AI security has gradually emerged. Most existing machine learning algorithms may be attacked by adversarial examples. An adversarial example is a slightly modified input sample that can lead to a false result of machine learning algorithms. The adversarial examples pose a potential security threat for many AI application areas, especially in the domain of robot path planning. In this field, the adversarial examples obstruct the algorithm by adding obstacles to the normal maps, resulting in multiple effects on the predicted path. However, there is no suitable approach to automatically identify them. To our knowledge, all previous work uses manual observation method to estimate the attack results of adversarial maps, which is time-consuming. Aiming at the existing problem, this paper explores a method to automatically identify the adversarial examples in Value Iteration Networks (VIN), which has a strong generalization ability. We analyze the possible scenarios caused by the adversarial maps. We propose a training-based identification approach to VIN adversarial examples by combing the path feature comparison and path image classification. We evaluate our method using the adversarial maps dataset, show that our method can achieve a high-accuracy and faster identification than manual observation method.

cs.CR↗
arXiv2018

Microsoft Dialogue Challenge: Building End-to-End Task-Completion Dialogue Systems

This proposal introduces a Dialogue Challenge for building end-to-end task-completion dialogue systems, with the goal of encouraging the dialogue research community to collaborate and benchmark on standard datasets and unified experimental environment. In this special session, we will release human-annotated conversational data in three domains (movie-ticket booking, restaurant reservation, and taxi booking), as well as an experiment platform with built-in simulators in each domain, for training and evaluation purposes. The final submitted systems will be evaluated both in simulated setting and by human judges.

cs.CL↗
arXiv2018

Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning

This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to improving the effectiveness and robustness of Deep Dyna-Q (DDQ), a recently proposed framework that extends the Dyna-Q algorithm to integrate planning for task-completion dialogue policy learning. To obviate DDQ's high dependency on the quality of simulated experiences, we incorporate an RNN-based discriminator in D3Q to differentiate simulated experience from real user experience in order to control the quality of training data. Experiments show that D3Q significantly outperforms DDQ by controlling the quality of simulated experience used for planning. The effectiveness and robustness of D3Q is further demonstrated in a domain extension setting, where the agent's capability of adapting to a changing environment is tested.

cs.CL↗
arXiv2018

Language-Based Image Editing with Recurrent Attentive Models

We investigate the problem of Language-Based Image Editing (LBIE). Given a source image and a natural language description, we want to generate a target image by editing the source image based on the description. We propose a generic modeling framework for two sub-tasks of LBIE: language-based image segmentation and image colorization. The framework uses recurrent attentive models to fuse image and language features. Instead of using a fixed step size, we introduce for each region of the image a termination gate to dynamically determine after each inference step whether to continue extrapolating additional information from the textual description. The effectiveness of the framework is validated on three datasets. First, we introduce a synthetic dataset, called CoSaL, to evaluate the end-to-end performance of our LBIE system. Second, we show that the framework leads to state-of-the-art performance on image segmentation on the ReferIt dataset. Third, we present the first language-based colorization result on the Oxford-102 Flowers dataset.

cs.CV↗
arXiv2018

Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning

Training a task-completion dialogue agent via reinforcement learning (RL) is costly because it requires many interactions with real users. One common alternative is to use a user simulator. However, a user simulator usually lacks the language complexity of human interlocutors and the biases in its design may tend to degrade the agent. To address these issues, we present Deep Dyna-Q, which to our knowledge is the first deep RL framework that integrates planning for task-completion dialogue policy learning. We incorporate into the dialogue agent a model of the environment, referred to as the world model, to mimic real user response and generate simulated experience. During dialogue policy learning, the world model is constantly updated with real user experience to approach real user behavior, and in turn, the dialogue agent is optimized using both real experience and simulated experience. The effectiveness of our approach is demonstrated on a movie-ticket booking task in both simulated and human-in-the-loop settings.

cs.CL↗
arXiv2018

Dynamic Fusion Networks for Machine Reading Comprehension

This paper presents a novel neural model - Dynamic Fusion Network (DFN), for machine reading comprehension (MRC). DFNs differ from most state-of-the-art models in their use of a dynamic multi-strategy attention process, in which passages, questions and answer candidates are jointly fused into attention vectors, along with a dynamic multi-step reasoning module for generating answers. With the use of reinforcement learning, for each input sample that consists of a question, a passage and a list of candidate answers, an instance of DFN with a sample-specific network architecture can be dynamically constructed by determining what attention strategy to apply and how many reasoning steps to take. Experiments show that DFNs achieve the best result reported on RACE, a challenging MRC dataset that contains real human reading questions in a wide variety of types. A detailed empirical analysis also demonstrates that DFNs can produce attention vectors that summarize information from questions, passages and answer candidates more effectively than other popular MRC models.

cs.CL↗
arXiv2018

Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning

This paper presents a new method --- adversarial advantage actor-critic (Adversarial A2C), which significantly improves the efficiency of dialogue policy learning in task-completion dialogue systems. Inspired by generative adversarial networks (GAN), we train a discriminator to differentiate responses/actions generated by dialogue agents from responses/actions by experts. Then, we incorporate the discriminator as another critic into the advantage actor-critic (A2C) framework, to encourage the dialogue agent to explore state-action within the regions where the agent takes actions similar to those of the experts. Experimental results in a movie-ticket booking domain show that the proposed Adversarial A2C can accelerate policy exploration efficiently.

cs.CL↗
arXiv2018

Image Disguise based on Generative Model

To protect image contents, most existing encryption algorithms are designed to transform an original image into a texture-like or noise-like image, which is, however, an obvious visual sign indicating the presence of an encrypted image, results in a significantly large number of attacks. To solve this problem, in this paper, we propose a new image encryption method to generate a visually same image as the original one by sending a meaning-normal and independent image to a corresponding well-trained generative model to achieve the effect of disguising the original image. This image disguise method not only solves the problem of obvious visual implication, but also guarantees the security of the information.

cs.CV↗
arXiv2017

Random Triggering Based Sub-Nyquist Sampling System for Sparse Multiband Signal

We propose a novel random triggering based modulated wideband compressive sampling (RT-MWCS) method to facilitate efficient realization of sub-Nyquist rate compressive sampling systems for sparse wideband signals. Under the assumption that the signal is repetitively (not necessarily periodically) triggered, RT-MWCS uses random modulation to obtain measurements of the signal at randomly chosen positions. It uses multiple measurement vector method to estimate the non-zero supports of the signal in the frequency domain. Then, the signal spectrum is solved using least square estimation. The distinct ability of estimating sparse multiband signal is facilitated with the use of level triggering and time to digital converter devices previously used in random equivalent sampling (RES) scheme. Compared to the existing compressive sampling (CS) techniques, such as modulated wideband converter (MWC), RT-MWCS is with simple system architecture and can be implemented with one channel at the cost of more sampling time. Experimental results indicate that, for sparse multiband signal with unknown spectral support, RT-MWCS requires a sampling rate much lower than Nyquist rate, while giving great quality of signal reconstruction.

cs.IT↗
arXiv2016

Multispectral Deep Neural Networks for Pedestrian Detection

Multispectral pedestrian detection is essential for around-the-clock applications, e.g., surveillance and autonomous driving. We deeply analyze Faster R-CNN for multispectral pedestrian detection task and then model it into a convolutional network (ConvNet) fusion problem. Further, we discover that ConvNet-based pedestrian detectors trained by color or thermal images separately provide complementary information in discriminating human instances. Thus there is a large potential to improve pedestrian detection by using color and thermal images in DNNs simultaneously. We carefully design four ConvNet fusion architectures that integrate two-branch ConvNets on different DNNs stages, all of which yield better performance compared with the baseline detector. Our experimental results on KAIST pedestrian benchmark show that the Halfway Fusion model that performs fusion on the middle-level convolutional features outperforms the baseline method by 11% and yields a missing rate 3.5% lower than the other proposed architectures.

cs.CV↗
arXiv2015

Quasi-coherent thermal emitter based on refractory plasmonic materials

The thermal emission of refractory plasmonic metamaterial - a titanium nitride 1D grating - is studied at high operating temperature (540 °C). By choosing a refractory material, we fabricate thermal gratings with high brightness that are emitting mid-infrared radiation centered around 3 $μ$m. We demonstrate experimentally that the thermal excitation of plasmon-polariton on the surface of the grating produces a well-collimated beam with a spatial coherence length of 32λ (angular divergence of 1.8°) which is quasi-monochromatic with a full width at half maximum of 70 nm. These experimental results show good agreement with a numerical model based on a two-dimensional full-wave analysis in frequency domain.

physics.optics↗
arXiv2013

Iterative Detection and Decoding for MIMO Systems with Knowledge-Aided Message Passing Algorithms

In this paper, we consider the problem of iterative detection and decoding (IDD) for multi-antenna systems using low-density parity-check (LDPC) codes. The proposed IDD system consists of a soft-input soft-output parallel interference (PIC) cancellation scheme with linear minimum mean-square error (MMSE) receive filters and two novel belief propagation (BP) decoding algorithms. The proposed BP algorithms exploit the knowledge of short cycles in the graph structure and the reweighting factors derived from the hypergraph's expansion. Simulation results show that when used to perform IDD for multi-antenna systems both proposed BP decoding algorithms can consistently outperform existing BP techniques with a small number of decoding iterations.

cs.IT↗