Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering

Open-domain Question Answering (OpenQA) is an important task in Natural Language Processing (NLP), which aims to answer a question in the form of natural language based on large-scale unstructured documents. Recently, there has been a surge in the amount of research literature on OpenQA, particularly on techniques that integrate with neural Machine Reading Comprehension (MRC). While these research works have advanced performance to new heights on benchmark datasets, they have been rarely covered in existing surveys on QA systems. In this work, we review the latest research trends in OpenQA, with particular attention to systems that incorporate neural MRC techniques. Specifically, we begin with revisiting the origin and development of OpenQA systems. We then introduce modern OpenQA architecture named ``Retriever-Reader'' and analyze the various systems that follow this architecture as well as the specific techniques adopted in each of the components. We then discuss key challenges to developing OpenQA systems and offer an analysis of benchmarks that are commonly used. We hope our work would enable researchers to be informed of the recent advancement and also the open challenges in OpenQA research, so as to stimulate further progress in this field.

Temporally-Continuous Probabilistic Prediction using Polynomial Trajectory Parameterization

A commonly-used representation for motion prediction of actors is a sequence of waypoints (comprising positions and orientations) for each actor at discrete future time-points. While this approach is simple and flexible, it can exhibit unrealistic higher-order derivatives (such as acceleration) and approximation errors at intermediate time steps. To address this issue we propose a simple and general representation for temporally continuous probabilistic trajectory prediction that is based on polynomial trajectory parameterization. We evaluate the proposed representation on supervised trajectory prediction tasks using two large self-driving data sets. The results show realistic higher-order derivatives and better accuracy at interpolated time-points, as well as the benefits of the inferred noise distributions over the trajectories. Extensive experimental studies based on existing state-of-the-art models demonstrate the effectiveness of the proposed approach relative to other representations in predicting the future motions of vehicle, bicyclist, and pedestrian traffic actors.

NeuroDiff: Scalable Differential Verification of Neural Networks using Fine-Grained Approximation

As neural networks make their way into safety-critical systems, where misbehavior can lead to catastrophes, there is a growing interest in certifying the equivalence of two structurally similar neural networks. For example, compression techniques are often used in practice for deploying trained neural networks on computationally- and energy-constrained devices, which raises the question of how faithfully the compressed network mimics the original network. Unfortunately, existing methods either focus on verifying a single network or rely on loose approximations to prove the equivalence of two networks. Due to overly conservative approximation, differential verification lacks scalability in terms of both accuracy and computational cost. To overcome these problems, we propose NeuroDiff, a symbolic and fine-grained approximation technique that drastically increases the accuracy of differential verification while achieving many orders-of-magnitude speedup. NeuroDiff has two key contributions. The first one is new convex approximations that more accurately bound the difference neurons of two networks under all possible inputs. The second one is judicious use of symbolic variables to represent neurons whose difference bounds have accumulated significant error. We also find that these two techniques are complementary, i.e., when combined, the benefit is greater than the sum of their individual benefits. We have evaluated NeuroDiff on a variety of differential verification tasks. Our results show that NeuroDiff is up to 1000X faster and 5X more accurate than the state-of-the-art tool.

Deep Learning Based Equalizer for MIMO-OFDM Systems with Insufficient Cyclic Prefix

In this paper, we study the equalization design for multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) systems with insufficient cyclic prefix (CP). In particular, the signal detection performance is severely impaired by inter-carrier interference (ICI) and inter-symbol interference (ISI) when the multipath delay spread exceeding the length of CP. To tackle this problem, a deep learning-based equalizer is proposed for approximating the maximum likelihood detection. Inspired by the dependency between the adjacent subcarriers, a computationally efficient joint detection scheme is developed. Employing the proposed equalizer, an iterative receiver is also constructed and the detection performance is evaluated through simulations over measured multipath channels. Our results reveal that the proposed receiver can achieve significant performance improvement compared to two traditional baseline schemes.

DiffRNN: Differential Verification of Recurrent Neural Networks

Recurrent neural networks (RNNs) such as Long Short Term Memory (LSTM) networks have become popular in a variety of applications such as image processing, data classification, speech recognition, and as controllers in autonomous systems. In practical settings, there is often a need to deploy such RNNs on resource-constrained platforms such as mobile phones or embedded devices. As the memory footprint and energy consumption of such components become a bottleneck, there is interest in compressing and optimizing such networks using a range of heuristic techniques. However, these techniques do not guarantee the safety of the optimized network, e.g., against adversarial inputs, or equivalence of the optimized and original networks. To address this problem, we propose DIFFRNN, the first differential verification method for RNNs to certify the equivalence of two structurally similar neural networks. Existing work on differential verification for ReLUbased feed-forward neural networks does not apply to RNNs where nonlinear activation functions such as Sigmoid and Tanh cannot be avoided. RNNs also pose unique challenges such as handling sequential inputs, complex feedback structures, and interactions between the gates and states. In DIFFRNN, we overcome these challenges by bounding nonlinear activation functions with linear constraints and then solving constrained optimization problems to compute tight bounding boxes on nonlinear surfaces in a high-dimensional space. The soundness of these bounding boxes is then proved using the dReal SMT solver. We demonstrate the practical efficacy of our technique on a variety of benchmarks and show that DIFFRNN outperforms state-of-the-art RNN verification tools such as POPQORN.

Limited-angle CT reconstruction via the L1/L2 minimization

In this paper, we consider minimizing the L1/L2 term on the gradient for a limit-angle scanning problem in computed tomography (CT) reconstruction. We design a splitting framework for both constrained and unconstrained optimization models. In addition, we can incorporate a box constraint that is reasonable for imaging applications. Numerical schemes are based on the alternating direction method of multipliers (ADMM), and we provide the convergence analysis of all the proposed algorithms (constrained/unconstrained and with/without the box constraint). Experimental results demonstrate the efficiency of our proposed approaches, showing significant improvements over the state-of-the-art methods in the limit-angle CT reconstruction. Specifically worth noticing is an exact recovery of the Shepp-Logan phantom from noiseless projection data with 30 scanning angle.

Bootstrapping Named Entity Recognition in E-Commerce with Positive Unlabeled Learning

Named Entity Recognition (NER) in domains like e-commerce is an understudied problem due to the lack of annotated datasets. Recognizing novel entity types in this domain, such as products, components, and attributes, is challenging because of their linguistic complexity and the low coverage of existing knowledge resources. To address this problem, we present a bootstrapped positive-unlabeled learning algorithm that integrates domain-specific linguistic features to quickly and efficiently expand the seed dictionary. The model achieves an average F1 score of 72.02% on a novel dataset of product descriptions, an improvement of 3.63% over a baseline BiLSTM classifier, and in particular exhibits better recall (4.96% on average).

An Artificial-intelligence/Statistics Solution to Quantify Material Distortion for Thermal Compensation in Additive Manufacturing

In this paper, we introduce a probabilistic statistics solution or artificial intelligence (AI) approach to identify and quantify permanent (non-zero strain) continuum/material deformation only based on the scanned material data in the spatial configuration and the shape of the initial design configuration or the material configuration. The challenge of this problem is that we only know the scanned material data in the spatial configuration and the shape of the design configuration of three-dimensional (3D) printed products, whereas for a specific scanned material point we do not know its corresponding material coordinates in the initial or designed referential configuration, provided that we do not know the detailed information on actual physical deformation process. Different from physics-based modeling, the method developed here is a data-driven artificial intelligence method, which solves the problem with incomplete deformation data or with missing information of actual physical deformation process. We coined the method is an AI-based material deformation finding algorithm. This method has practical significance and important applications in finding and designing thermal compensation configuration of a 3D printed product in additive manufacturing, which is at the heart of the cutting edge 3D printing technology. In this paper, we demonstrate that the proposed AI continuum/material deformation finding approach can accurately find permanent thermal deformation configuration for a complex 3D printed structure component, and hence to identify the thermal compensation design configuration in order to minimizing the impact of temperature fluctuations on 3D printed structure components that are sensitive to changes of temperature.

LSHR-Net: a hardware-friendly solution for high-resolution computational imaging using a mixed-weights neural network

Recent work showed neural-network-based approaches to reconstructing images from compressively sensed measurements offer significant improvements in accuracy and signal compression. Such methods can dramatically boost the capability of computational imaging hardware. However, to date, there have been two major drawbacks: (1) the high-precision real-valued sensing patterns proposed in the majority of existing works can prove problematic when used with computational imaging hardware such as a digital micromirror sampling device and (2) the network structures for image reconstruction involve intensive computation, which is also not suitable for hardware deployment. To address these problems, we propose a novel hardware-friendly solution based on mixed-weights neural networks for computational imaging. In particular, learned binary-weight sensing patterns are tailored to the sampling device. Moreover, we proposed a recursive network structure for low-resolution image sampling and high-resolution reconstruction scheme. It reduces both the required number of measurements and reconstruction computation by operating convolution on small intermediate feature maps. The recursive structure further reduced the model size, making the network more computationally efficient when deployed with the hardware. Our method has been validated on benchmark datasets and achieved the state of the art reconstruction accuracy. We tested our proposed network in conjunction with a proof-of-concept hardware setup.

TCNN: Triple Convolutional Neural Network Models for Retrieval-based Question Answering System in E-commerce

Automatic question-answering (QA) systems have boomed during last few years, and commonly used techniques can be roughly categorized into Information Retrieval (IR)-based and generation-based. A key solution to the IR based models is to retrieve the most similar knowledge entries of a given query from a QA knowledge base, and then rerank those knowledge entries with semantic matching models. In this paper, we aim to improve an IR based e-commerce QA system-AliMe with proposed text matching models, including a basic Triple Convolutional Neural Network (TCNN) model and two Attention-based TCNN (ATCNN) models. Experimental results show their effect.