arXiv subjects

Xiaodong Liu

Publications and source records attributed to Xiaodong Liu.

At least 181 records · Page 10Linked to original sources

arXiv2020

Multi-Modality Cascaded Fusion Technology for Autonomous Driving

Multi-modality fusion is the guarantee of the stability of autonomous driving systems. In this paper, we propose a general multi-modality cascaded fusion framework, exploiting the advantages of decision-level and feature-level fusion, utilizing target position, size, velocity, appearance and confidence to achieve accurate fusion results. In the fusion process, dynamic coordinate alignment(DCA) is conducted to reduce the error between sensors from different modalities. In addition, the calculation of affinity matrix is the core module of sensor fusion, we propose an affinity loss that improves the performance of deep affinity network(DAN). Last, the proposed step-by-step cascaded fusion framework is more interpretable and flexible compared to the end-toend fusion methods. Extensive experiments on Nuscenes [2] dataset show that our approach achieves the state-of-theart performance.dataset show that our approach achieves the state-of-the-art performance.

cs.CV↗

arXiv2020

Identification of point like objects with multi-frequency sparse data

The inverse acoustic scattering of point objects using multi-frequency sparse measurements are studied. The objects may be a sum of point sources or point like scatterers. We show that the locations and scattering strengths of the point objects can be uniquely identified by the multi-frequency near or far fields taken at sparse sensors. Based on the uniqueness analysis, some direct methods have also been proposed for reconstructing the locations and determining the scattering strengths. The numerical examples are conducted to show the validity and robustness of the proposed numerical methods.

math.AP↗

arXiv2019

FFDNet-Based Channel Estimation for Massive MIMO Visible Light Communication Systems

Channel estimation is of crucial importance in massive multiple-input multiple-output (m-MIMO) visible light communication (VLC) systems. In order to tackle this problem, a fast and flexible denoising convolutional neural network (FFDNet)-based channel estimation scheme for m-MIMO VLC systems was proposed. The channel matrix of the m-MIMO VLC channel is identified as a two-dimensional natural image since the channel has the characteristic of sparsity. A deep learning-enabled image denoising network FFDNet is exploited to learn from a large number of training data and to estimate the m-MIMO VLC channel. Simulation results demonstrate that our proposed channel estimation based on the FFDNet significantly outperforms the benchmark scheme based on minimum mean square error.

eess.SP↗

arXiv2019

Inverse acoustic scattering problems with multi-frequency sparse backscattering far field data

The inverse acoustic scattering problems using multi-frequency backscattering far field patterns at isolated directions are studied. The underlying object could be point like scatterers, small scatterers, extended inhomogeneities and obstacles. A fast and robust direct sampling method is proposed for location and shape reconstruction of the underlying objects. To our best knowledge, this is the first numerical method for inverse obstacle/medium scattering problems with the multi-frequency sparse backscattering data. Some approximate uniqueness results have also been showed based on the weak scattering approximation and the Kirchhoff approximation. The theoretical basis of the direct sampling method is initially established based on these two approximations. Numerical examples in two dimensions are presented to validity the effectiveness and robustness of the proposed direct sampling method. In particular, the numerical reconstructions indicate that the direct sampling method also works very well beyond these two approximations.

math.AP↗

arXiv2019

Unified Language Model Pre-training for Natural Language Understanding and Generation

This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks. The model is pre-trained using three types of language modeling tasks: unidirectional, bidirectional, and sequence-to-sequence prediction. The unified modeling is achieved by employing a shared Transformer network and utilizing specific self-attention masks to control what context the prediction conditions on. UniLM compares favorably with BERT on the GLUE benchmark, and the SQuAD 2.0 and CoQA question answering tasks. Moreover, UniLM achieves new state-of-the-art results on five natural language generation datasets, including improving the CNN/DailyMail abstractive summarization ROUGE-L to 40.51 (2.04 absolute improvement), the Gigaword abstractive summarization ROUGE-L to 35.75 (0.86 absolute improvement), the CoQA generative question answering F1 score to 82.5 (37.1 absolute improvement), the SQuAD question generation BLEU-4 to 22.12 (3.75 absolute improvement), and the DSTC7 document-grounded dialog response generation NIST-4 to 2.67 (human performance is 2.65). The code and pre-trained models are available at https://github.com/microsoft/unilm.

cs.CL↗

arXiv2019

Performance Analysis on Visible Light Communications With Multi-Eavesdroppers and Practical Amplitude Constraint

In this paper the secure performance for the visible light communication (VLC) system with multiple eavesdroppers is studied. By considering the practical amplitude constraint instead of an average power constraint in the VLC system, the closed-form expressions for the upper and the lower bounds of the secrecy outage probability and the average secrecy capacity are derived. Since the locations for both legitimate receiver and eavesdroppers are unknown as well as random, the stochastic geometry method is introduced for problem formulation. Moreover, accurate expressions with a low computational complexity are obtained with the rigorous derivation. Simulation results verify the correctness of our theoretical analysis.

eess.SP↗

arXiv2019

A Hybrid Retrieval-Generation Neural Conversation Model

Intelligent personal assistant systems that are able to have multi-turn conversations with human users are becoming increasingly popular. Most previous research has been focused on using either retrieval-based or generation-based methods to develop such systems. Retrieval-based methods have the advantage of returning fluent and informative responses with great diversity. However, the performance of the methods is limited by the size of the response repository. On the other hand, generation-based methods can produce highly coherent responses on any topics. But the generated responses are often generic and not informative due to the lack of grounding knowledge. In this paper, we propose a hybrid neural conversation model that combines the merits of both response retrieval and generation methods. Experimental results on Twitter and Foursquare data show that the proposed model outperforms both retrieval-based methods and generation-based methods (including a recently proposed knowledge-grounded neural conversation model) under both automatic evaluation metrics and human evaluation. We hope that the findings in this study provide new insights on how to integrate text retrieval and text generation models for building conversation systems.

cs.IR↗

arXiv2019

Adversarial Domain Adaptation for Machine Reading Comprehension

In this paper, we focus on unsupervised domain adaptation for Machine Reading Comprehension (MRC), where the source domain has a large amount of labeled data, while only unlabeled passages are available in the target domain. To this end, we propose an Adversarial Domain Adaptation framework (AdaMRC), where ($i$) pseudo questions are first generated for unlabeled passages in the target domain, and then ($ii$) a domain classifier is incorporated into an MRC model to predict which domain a given passage-question pair comes from. The classifier and the passage-question encoder are jointly trained using adversarial learning to enforce domain-invariant representation learning. Comprehensive evaluations demonstrate that our approach ($i$) is generalizable to different MRC models and datasets, ($ii$) can be combined with pre-trained large-scale language models (such as ELMo and BERT), and ($iii$) can be extended to semi-supervised learning.

cs.CL↗

arXiv2019

The Learning of Fuzzy Cognitive Maps With Noisy Data: A Rapid and Robust Learning Method With Maximum Entropy

Numerous learning methods for fuzzy cognitive maps (FCMs), such as the Hebbian-based and the population-based learning methods, have been developed for modeling and simulating dynamic systems. However, these methods are faced with several obvious limitations. Most of these models are extremely time consuming when learning the large-scale FCMs with hundreds of nodes. Furthermore, the FCMs learned by those algorithms lack robustness when the experimental data contain noise. In addition, reasonable distribution of the weights is rarely considered in these algorithms, which could result in the reduction of the performance of the resulting FCM. In this article, a straightforward, rapid, and robust learning method is proposed to learn FCMs from noisy data, especially, to learn large-scale FCMs. The crux of the proposed algorithm is to equivalently transform the learning problem of FCMs to a classic-constrained convex optimization problem in which the least-squares term ensures the robustness of the well-learned FCM and the maximum entropy term regularizes the distribution of the weights of the well-learned FCM. A series of experiments covering two frequently used activation functions (the sigmoid and hyperbolic tangent functions) are performed on both synthetic datasets with noise and real-world datasets. The experimental results show that the proposed method is rapid and robust against data containing noise and that the well-learned weights have better distribution. In addition, the FCMs learned by the proposed method also exhibit superior performance in comparison with the existing methods. Index Terms-Fuzzy cognitive maps (FCMs), maximum entropy, noisy data, rapid and robust learning.

cs.LG↗

arXiv2019

Symmetry-preserving WENO limiters

Weighted essentially non-oscillatory (WENO) reconstruction schemes are presented that preserve cylindrical symmetry for radial flows on an equal-angle polar mesh. These new WENO schemes are used with a Lagrangian discontinuous Galerkin (DG) hydrodynamic method. The solution polynomials are reconstructed using the WENO schemes where the DG solution is the central stencil. A suite of challenging test problems are calculated to demonstrate the accuracy and robustness of the new WENO schemes.

physics.comp-ph↗

arXiv2019

A Hybrid Neural Network Model for Commonsense Reasoning

This paper proposes a hybrid neural network (HNN) model for commonsense reasoning. An HNN consists of two component models, a masked language model and a semantic similarity model, which share a BERT-based contextual encoder but use different model-specific input and output layers. HNN obtains new state-of-the-art results on three classic commonsense reasoning tasks, pushing the WNLI benchmark to 89%, the Winograd Schema Challenge (WSC) benchmark to 75.1%, and the PDP60 benchmark to 90.0%. An ablation study shows that language models and semantic similarity models are complementary approaches to commonsense reasoning, and HNN effectively combines the strengths of both. The code and pre-trained models will be publicly available at https://github.com/namisan/mt-dnn.

cs.CL↗

arXiv2019

DoubleTransfer at MEDIQA 2019: Multi-Source Transfer Learning for Natural Language Understanding in the Medical Domain

This paper describes our competing system to enter the MEDIQA-2019 competition. We use a multi-source transfer learning approach to transfer the knowledge from MT-DNN and SciBERT to natural language understanding tasks in the medical domain. For transfer learning fine-tuning, we use multi-task learning on NLI, RQE and QA tasks on general and medical domains to improve performance. The proposed methods are proved effective for natural language understanding in the medical domain, and we rank the first place on the QA task.

cs.CL↗

arXiv2019

Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing

Variational autoencoders (VAEs) with an auto-regressive decoder have been applied for many natural language processing (NLP) tasks. The VAE objective consists of two terms, (i) reconstruction and (ii) KL regularization, balanced by a weighting hyper-parameter β. One notorious training difficulty is that the KL term tends to vanish. In this paper we study scheduling schemes for β, and show that KL vanishing is caused by the lack of good latent codes in training the decoder at the beginning of optimization. To remedy this, we propose a cyclical annealing schedule, which repeats the process of increasing βmultiple times. This new procedure allows the progressive learning of more meaningful latent codes, by leveraging the informative representations of previous cycles as warm re-starts. The effectiveness of cyclical annealing is validated on a broad range of NLP tasks, including language modeling, dialog response generation and unsupervised language pre-training.

cs.LG↗

arXiv2019

Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading

Although neural conversation models are effective in learning how to produce fluent responses, their primary challenge lies in knowing what to say to make the conversation contentful and non-vacuous. We present a new end-to-end approach to contentful neural conversation that jointly models response generation and on-demand machine reading. The key idea is to provide the conversation model with relevant long-form text on the fly as a source of external knowledge. The model performs QA-style reading comprehension on this text in response to each conversational turn, thereby allowing for more focused integration of external knowledge than has been possible in prior approaches. To support further research on knowledge-grounded conversation, we introduce a new large-scale conversation dataset grounded in external web pages (2.8M turns, 7.4M sentences of grounding). Both human evaluation and automated metrics show that our approach results in more contentful responses compared to a variety of previous methods, improving both the informativeness and diversity of generated output.

cs.CL↗

arXiv2019

Inverse electromagnetic source scattering problems with multi-frequency sparse phased and phaseless far field data

This paper is concerned with uniqueness, phase retrieval and shape reconstruction methods for solving inverse electromagnetic source scattering problems with multi-frequency sparse phased or phaseless far field data. With the phased data, we show that the smallest strip containing the source support with the observation direction as the normal can be uniquely determined by the multi-frequency far field pattern at a single observation direction. A phased direct sampling method is also proposed to reconstruct the strip. The phaseless far field data is closely related to the outward energy flux, which can be measured more easily in practice. We show that the phaseless far field data is invariant under the translation of the sources, which implies that the location of the sources can not be uniquely recovered by the data. To solve this problem, we consider simultaneously the scattering of magnetic dipoles with one fixed source point and at most three scattering strengths. With this technique, a fast and stable phase retrieval approach is proposed based on a simple geometrical result which provides a stable reconstruction of a point in the plane from three distances to the given points. A novel phaseless direct sampling method is also proposed to reconstruct the strip. The phase retrieval approach can also be combined with the phased direct sampling method to reconstruct the strip. Finally, to obtain a source support, we just need to superpose the indicators with respect to the sparse observation directions. Extended numerical examples in three dimensions are conducted with noisy data, and the results further verify the effectiveness and robustness of the proposed phase retrieval approach and direct sampling methods.

math.AP↗

arXiv2019

Multi-Task Deep Neural Networks for Natural Language Understanding

In this paper, we present a Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple natural language understanding (NLU) tasks. MT-DNN not only leverages large amounts of cross-task data, but also benefits from a regularization effect that leads to more general representations in order to adapt to new tasks and domains. MT-DNN extends the model proposed in Liu et al. (2015) by incorporating a pre-trained bidirectional transformer language model, known as BERT (Devlin et al., 2018). MT-DNN obtains new state-of-the-art results on ten NLU tasks, including SNLI, SciTail, and eight out of nine GLUE tasks, pushing the GLUE benchmark to 82.7% (2.2% absolute improvement). We also demonstrate using the SNLI and SciTail datasets that the representations learned by MT-DNN allow domain adaptation with substantially fewer in-domain labels than the pre-trained BERT representations. The code and pre-trained models are publicly available at https://github.com/namisan/mt-dnn.

cs.CL↗

arXiv2019

Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding

This paper explores the use of knowledge distillation to improve a Multi-Task Deep Neural Network (MT-DNN) (Liu et al., 2019) for learning text representations across multiple natural language understanding tasks. Although ensemble learning can improve model performance, serving an ensemble of large DNNs such as MT-DNN can be prohibitively expensive. Here we apply the knowledge distillation method (Hinton et al., 2015) in the multi-task learning setting. For each task, we train an ensemble of different MT-DNNs (teacher) that outperforms any single model, and then train a single MT-DNN (student) via multi-task learning to \emph{distill} knowledge from these ensemble teachers. We show that the distilled MT-DNN significantly outperforms the original MT-DNN on 7 out of 9 GLUE tasks, pushing the GLUE benchmark (single model) to 83.7\% (1.5\% absolute improvement\footnote{ Based on the GLUE leaderboard at https://gluebenchmark.com/leaderboard as of April 1, 2019.}). The code and pre-trained models will be made publicly available at https://github.com/namisan/mt-dnn.

cs.CL↗

arXiv2019

Unsupervised Deep Structured Semantic Models for Commonsense Reasoning

Commonsense reasoning is fundamental to natural language understanding. While traditional methods rely heavily on human-crafted features and knowledge bases, we explore learning commonsense knowledge from a large amount of raw text via unsupervised learning. We propose two neural network models based on the Deep Structured Semantic Models (DSSM) framework to tackle two classic commonsense reasoning tasks, Winograd Schema challenges (WSC) and Pronoun Disambiguation (PDP). Evaluation shows that the proposed models effectively capture contextual information in the sentence and co-reference information between pronouns and nouns, and achieve significant improvement over previous state-of-the-art approaches.

cs.CL↗