PyTorchKR Papers

최신 논문

총 3,337편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2109.01238공식 코드 · Papers with Code

An Empirical Study on Leveraging Position Embeddings for Target-oriented Opinion Words Extraction

Target-oriented opinion words extraction (TOWE) (Fan et al., 2019b) is a new subtask of target-oriented sentiment analysis that aims to extract opinion words for a given aspect in text. Current state-of-the-art methods leverage position embeddings to capture the relative position of a word to the target. However, the performance of these methods depends on the ability to incorporate this information into word representations. In this paper, we explore a variety of text encoders based on pretrained word embeddings or language models that leverage part-of-speech and position embeddings, aiming to examine the actual contribution of each component in TOWE. We also adapt a graph convolutional network (GCN) to enhance word representations by incorporating syntactic information. Our experimental results demonstrate that BiLSTM-based models can effectively encode position information into word representations while using a GCN only achieves marginal gains. Interestingly, our simple methods outperform several state-of-the-art complex neural structures.

arXiv:2109.00442

Position Masking for Improved Layout-Aware Document Understanding

Natural language processing for document scans and PDFs has the potential to enormously improve the efficiency of business processes. Layout-aware word embeddings such as LayoutLM have shown promise for classification of and information extraction from such documents. This paper proposes a new pre-training task called that can improve performance of layout-aware word embeddings that incorporate 2-D position embeddings. We compare models pre-trained with only language masking against models pre-trained with both language masking and position masking, and we find that position masking improves performance by over 5% on a form understanding task.

arXiv:2109.00101

Position-based Hash Embeddings For Scaling Graph Neural Networks

Graph Neural Networks (GNNs) bring the power of deep representation learning to graph and relational data and achieve state-of-the-art performance in many applications. GNNs compute node representations by taking into account the topology of the node's ego-network and the features of the ego-network's nodes. When the nodes do not have high-quality features, GNNs learn an embedding layer to compute node embeddings and use them as input features. However, the size of the embedding layer is linear to the product of the number of nodes in the graph and the dimensionality of the embedding and does not scale to big data and graphs with hundreds of millions of nodes. To reduce the memory associated with this embedding layer, hashing-based approaches, commonly used in applications like NLP and recommender systems, can potentially be used. However, a direct application of these ideas fails to exploit the fact that in many real-world graphs, nodes that are topologically close will tend to be related to each other (homophily) and as such their representations will be similar. In this work, we present approaches that take advantage of the nodes' position in the graph to dramatically reduce the memory required, with minimal if any degradation in the quality of the resulting GNN model. Our approaches decompose a node's embedding into two components: a position-specific component and a node-specific component. The position-specific component models homophily and the node-specific component models the node-to-node variation. Extensive experiments using different datasets and GNN models show that our methods are able to reduce the memory requirements by 88% to 97% while achieving, in nearly all cases, better classification accuracy than other competing approaches, including the full embeddings.

arXiv:2109.00256

Extracting all Aspect-polarity Pairs Jointly in a Text with Relation Extraction Approach

Extracting aspect-polarity pairs from texts is an important task of fine-grained sentiment analysis. While the existing approaches to this task have gained many progresses, they are limited at capturing relationships among aspect-polarity pairs in a text, thus degrading the extraction performance. Moreover, the existing state-of-the-art approaches, namely token-based se-quence tagging and span-based classification, have their own defects such as polarity inconsistency resulted from separately tagging tokens in the former and the heterogeneous categorization in the latter where aspect-related and polarity-related labels are mixed. In order to remedy the above defects, in-spiring from the recent advancements in relation extraction, we propose to generate aspect-polarity pairs directly from a text with relation extraction technology, regarding aspect-pairs as unary relations where aspects are enti-ties and the corresponding polarities are relations. Based on the perspective, we present a position- and aspect-aware sequence2sequence model for joint extraction of aspect-polarity pairs. The model is characterized with its ability to capture not only relationships among aspect-polarity pairs in a text through the sequence decoding, but also correlations between an aspect and its polarity through the position- and aspect-aware attentions. The experi-ments performed on three benchmark datasets demonstrate that our model outperforms the existing state-of-the-art approaches, making significant im-provement over them.

arXiv:2004.00795

The Role of Bounded Fields-of-View and Negative Information in Finite Set Statistics (FISST)

The role of negative information is particularly important to search-detect-track problems in which the number of objects is unknown a priori, and the size of the sensor field-of-view is far smaller than that of the region of interest. This paper presents an approach for systematically incorporating knowledge of the field-of-view geometry and position and object inclusion/exclusion evidence into object state densities and random finite set multi-object cardinality distributions. The approach is derived for a representative set of multi-object distributions and demonstrated through a sensor planning problem involving a multi-Bernoulli process with up to one-hundred potential targets.

arXiv:2108.13831

Deep Learning of Transferable MIMO Channel Modes for 6G V2X Communications

In the emerging high mobility Vehicle-to-Everything (V2X) communications using millimeter Wave (mmWave) and sub-THz, Multiple-Input Multiple-Output (MIMO) channel estimation is an extremely challenging task. At mmWaves/sub-THz frequencies, MIMO channels exhibit few leading paths in the space-time domain (i.e., directions or arrival/departure and delays). Algebraic Low-rank (LR) channel estimation exploits space-time channel sparsity through the computation of position-dependent MIMO channel eigenmodes leveraging recurrent training vehicle passages in the coverage cell. LR requires vehicles' geographical positions and tens to hundreds of training vehicles' passages for each position, leading to significant complexity and control signalling overhead. Here we design a DL-based LR channel estimation method to infer MIMO channel eigenmodes in V2X urban settings, starting from a single LS channel estimate and without needing vehicle's position information. Numerical results show that the proposed method attains comparable Mean Squared Error (MSE) performance as the position-based LR. Moreover, we show that the proposed model can be trained on a reference scenario and be effectively transferred to urban contexts with different space-time channel features, providing comparable MSE performance without an explicit transfer learning procedure. This result eases the deployment in arbitrary dense urban scenarios.

arXiv:2108.13766

The five Is: Key principles for interpretable and safe conversational AI

In this position paper, we present five key principles, namely interpretability, inherent capability to explain, independent data, interactive learning, and inquisitiveness, for the development of conversational AI that, unlike the currently popular black box approaches, is transparent and accountable. At present, there is a growing concern with the use of black box statistical language models: While displaying impressive average performance, such systems are also prone to occasional spectacular failures, for which there is no clear remedy. In an effort to initiate a discussion on possible alternatives, we outline and exemplify how our five principles enable the development of conversational AI systems that are transparent and thus safer for use. We also present some of the challenges inherent in the implementation of those principles.

arXiv:2108.13202공식 코드 · Papers with Code

PTRAIL -- A python package for parallel trajectory data preprocessing

Trajectory data represent a trace of an object that changes its position in space over time. This kind of data is complex to handle and analyze, since it is generally produced in huge quantities, often prone to errors generated by the geolocation device, human mishandling, or area coverage limitation. Therefore, there is a need for software specifically tailored to preprocess trajectory data. In this work we propose PTRAIL, a python package offering several trajectory preprocessing steps, including filtering, feature extraction, and interpolation. PTRAIL uses parallel computation and vectorization, being suitable for large datasets and fast compared to other python libraries.

arXiv:2108.13344공식 코드 · Papers with Code

Enlisting 3D Crop Models and GANs for More Data Efficient and Generalizable Fruit Detection

Training real-world neural network models to achieve high performance and generalizability typically requires a substantial amount of labeled data, spanning a broad range of variation. This data-labeling process can be both labor and cost intensive. To achieve desirable predictive performance, a trained model is typically applied into a domain where the data distribution is similar to the training dataset. However, for many agricultural machine learning problems, training datasets are collected at a specific location, during a specific period in time of the growing season. Since agricultural systems exhibit substantial variability in terms of crop type, cultivar, management, seasonal growth dynamics, lighting condition, sensor type, etc, a model trained from one dataset often does not generalize well across domains. To enable more data efficient and generalizable neural network models in agriculture, we propose a method that generates photorealistic agricultural images from a synthetic 3D crop model domain into real world crop domains. The method uses a semantically constrained GAN (generative adversarial network) to preserve the fruit position and geometry. We observe that a baseline CycleGAN method generates visually realistic target domain images but does not preserve fruit position information while our method maintains fruit positions well. Image generation results in vineyard grape day and night images show the visual outputs of our network are much better compared to a baseline network. Incremental training experiments in vineyard grape detection tasks show that the images generated from our method can significantly speed the domain adaption process, increase performance for a given number of labeled images (i.e. data efficiency), and decrease labeling requirements.

arXiv:2108.12876

Solving Viewing Graph Optimization for Simultaneous Position and Rotation Registration

A viewing graph is a set of unknown camera poses, as the vertices, and the observed relative motions, as the edges. Solving the viewing graph is an essential step in a Structure-from-Motion procedure, where a set of relative motions is obtained from a collection of 2D images. Almost all methods in the literature solve for the rotations separately, through rotation averaging process, and use them for solving the positions. Obtaining positions is the challenging part because the translation observations only tell the direction of the motions. It becomes more challenging when the set of edges comprises pairwise translation observations between either near and far cameras. In this paper an iterative method is proposed that overcomes these issues. Also a method is proposed which obtains the rotations and positions simultaneously. Experimental results show the-state-of-the-art performance of the proposed methods.

arXiv:2108.12409공식 코드 · Papers with Code

Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

Since the introduction of the transformer model by Vaswani et al. (2017), a fundamental question has yet to be answered: how does a model achieve extrapolation at inference time for sequences that are longer than it saw during training? We first show that extrapolation can be enabled by simply changing the position representation method, though we find that current methods do not allow for efficient extrapolation. We therefore introduce a simpler and more efficient position method, Attention with Linear Biases (ALiBi). ALiBi does not add positional embeddings to word embeddings; instead, it biases query-key attention scores with a penalty that is proportional to their distance. We show that this method trains a 1.3 billion parameter model on input sequences of length 1024 that extrapolates to input sequences of length 2048, achieving the same perplexity as a sinusoidal position embedding model trained on inputs of length 2048 but training 11% faster and using 11% less memory. ALiBi's inductive bias towards recency also leads it to outperform multiple strong position methods on the WikiText-103 benchmark.

arXiv:2108.11943

Position-Invariant Truecasing with a Word-and-Character Hierarchical Recurrent Neural Network

Truecasing is the task of restoring the correct case (uppercase or lowercase) of noisy text generated either by an automatic system for speech recognition or machine translation or by humans. It improves the performance of downstream NLP tasks such as named entity recognition and language modeling. We propose a fast, accurate and compact two-level hierarchical word-and-character-based recurrent neural network model, the first of its kind for this problem. Using sequence distillation, we also address the problem of truecasing while ignoring token positions in the sentence, i.e. in a position-invariant manner.

arXiv:2108.11866

Geometric Stochastic Filter with Guaranteed Performance for Autonomous Navigation based on IMU and Feature Sensor Fusion

This paper concerns the estimation problem of attitude, position, and linear velocity of a rigid-body autonomously navigating with six degrees of freedom (6 DoF). The navigation dynamics are highly nonlinear and are modeled on the matrix Lie group of the extended Special Euclidean Group $\mathbb{SE}_{2}(3)$. A computationally cheap geometric nonlinear stochastic navigation filter is proposed on $\mathbb{SE}_{2}(3)$ with guaranteed transient and steady-state performance. The proposed filter operates based on a fusion of sensor measurements collected by a low-cost inertial measurement unit (IMU) and features (obtained by a vision unit). The closed loop error signals are guaranteed to be almost semi-globally uniformly ultimately bounded in the mean square from almost any initial condition. The equivalent quaternion representation is included in the Appendix. The filter is proposed in continuous form, and its discrete form is tested on a real-world dataset of measurements collected by a quadrotor navigating in three dimensional (3D) space. Keywords: Localization, navigation, position and orientation estimation, stochastic systems, GPS-denied navigation observer, navigation estimator, vision-aided inertial navigation systems (VA-INSs), stochastic differential equation, Gaussian noise, sensor fusion.

arXiv:2108.11604

Identification of the Resting Position Based on EGG, ECG, Respiration Rate and SpO2 Using Stacked Ensemble Learning

Rest is essential for a high-level physiological and psychological performance. It is also necessary for the muscles to repair, rebuild, and strengthen. There is a significant correlation between the quality of rest and the resting posture. Therefore, identification of the resting position is of paramount importance to maintain a healthy life. Resting postures can be classified into four basic categories: Lying on the back (supine), facing of the left / right sides and free-fall position. The later position is already considered to be an unhealthy posture by researchers equivocally and hence can be eliminated. In this paper, we analyzed the other three states of resting position based on the data collected from the physiological parameters: Electrogastrogram (EGG), Electrocardiogram (ECG), Respiration Rate, Heart Rate, and Oxygen Saturation (SpO2). Based on these parameters, the resting position is classified using a hybrid stacked ensemble machine learning model designed using the Decision tree, Random Forest, and Xgboost algorithms. Our study demonstrates a 100% accurate prediction of the resting position using the hybrid model. The proposed method of identifying the resting position based on physiological parameters has the potential to be integrated into wearable devices. This is a low cost, highly accurate and autonomous technique to monitor the body posture while maintaining the user privacy by eliminating the use of RGB camera conventionally used to conduct the polysomnography (sleep Monitoring) or resting position studies.

arXiv:2108.11321

Adaptive Extended Kalman Filter (ROSE-Filter) for Positioning System

This paper illustrates the way for estimating position and orientation of a vehicle with an Extended Kalman Filter (EKF). For this purpose a non-linear model is designed and an adaptive calculation of measurement noise covariance matrix is used, a so called ROSE-Filter (Rapid Ongoing Stochastic covariance Estimation-Filter). Input of the system is the measured position from a two dimensional position system. Estimated is the pose (position and orientation) and the velocity of the vehicle.

arXiv:2108.10613

Outdoor Position Recovery from HeterogeneousTelco Cellular Data

Recent years have witnessed unprecedented amounts of data generated by telecommunication (Telco) cellular networks. For example, measurement records (MRs) are generated to report the connection states between mobile devices and Telco networks, e.g., received signal strength. MR data have been widely used to localize outdoor mobile devices for human mobility analysis, urban planning, and traffic forecasting. Existing works using first-order sequence models such as the Hidden Markov Model (HMM) attempt to capture spatio-temporal locality in underlying mobility patterns for lower localization errors. The HMM approaches typically assume stable mobility patterns of the underlying mobile devices. Yet real MR datasets exhibit heterogeneous mobility patterns due to mixed transportation modes of the underlying mobile devices and uneven distribution of the positions associated with MR samples. Thus, the existing solutions cannot handle these heterogeneous mobility patterns. we propose a multi-task learning-based deep neural network (DNN) framework, namely PRNet+, to incorporate outdoor position recovery and transportation mode detection. To make sure the framework work, PRNet+ develops a feature extraction module to precisely learn local-, short- and long-term spatio-temporal locality from heterogeneous MR samples. Extensive evaluation on eight datasets collected at three representative areas in Shanghai indicates that PRNet+ greatly outperforms state-of-the-arts.

arXiv:2108.09779공식 코드 · Papers with Code

Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFinger

We present a system for learning a challenging dexterous manipulation task involving moving a cube to an arbitrary 6-DoF pose with only 3-fingers trained with NVIDIA's IsaacGym simulator. We show empirical benefits, both in simulation and sim-to-real transfer, of using keypoints as opposed to position+quaternion representations for the object pose in 6-DoF for policy observations and in reward calculation to train a model-free reinforcement learning agent. By utilizing domain randomization strategies along with the keypoint representation of the pose of the manipulated object, we achieve a high success rate of 83% on a remote TriFinger system maintained by the organizers of the Real Robot Challenge. With the aim of assisting further research in learning in-hand manipulation, we make the codebase of our system, along with trained checkpoints that come with billions of steps of experience available, at https://s2r2-ig.github.io

arXiv:2108.10222

Cooperative Localization Utilizing Reinforcement Learning for 5G Networks

The demand for accurate localization has risen in recent years to enable the emerging of autonomous vehicles. To have these vehicles in the traffic ecosystem of smart cities, the need for an accurate positioning system is emphasized. To realize accurate positioning, collaborative localization plays an important role. This type of localization computes range measurements between vehicles and improves the accuracy of position by correcting the possibly faulty values of one of them by using the more accurate values of the other. 5G signals with the technology of Millimeter Wave (mmWave) support precise range measurements and 5G networks provide Device to Device (D2D) communication which improves collaborative localization. The aim of this paper is to provide an accurate collaborative positioning for autonomous vehicles, which is less prone to errors utilizing reinforcement learning technique for selecting the most accurate and suitable range measurement technique for the 5G signal.

arXiv:2108.09691

Guiding Query Position and Performing Similar Attention for Transformer-Based Detection Heads

After DETR was proposed, this novel transformer-based detection paradigm which performs several cross-attentions between object queries and feature maps for predictions has subsequently derived a series of transformer-based detection heads. These models iterate object queries after each cross-attention. However, they don't renew the query position which indicates object queries' position information. Thus model needs extra learning to figure out the newest regions that query position should express and need more attention. To fix this issue, we propose the Guided Query Position (GQPos) method to embed the latest location information of object queries to query position iteratively. Another problem of such transformer-based detection heads is the high complexity to perform attention on multi-scale feature maps, which hinders them from improving detection performance at all scales. Therefore we propose a novel fusion scheme named Similar Attention (SiA): besides the feature maps is fused, SiA also fuse the attention weights maps to accelerate the learning of high-resolution attention weight map by well-learned low-resolution attention weight map. Our experiments show that the proposed GQPos improves the performance of a series of models, including DETR, SMCA, YoloS, and HoiTransformer and SiA consistently improve the performance of multi-scale transformer-based detection heads like DETR and HoiTransformer.

arXiv:2108.08538공식 코드 · Papers with Code

Mixture-Based Correction for Position and Trust Bias in Counterfactual Learning to Rank

In counterfactual learning to rank (CLTR) user interactions are used as a source of supervision. Since user interactions come with bias, an important focus of research in this field lies in developing methods to correct for the bias of interactions. Inverse propensity scoring (IPS) is a popular method suitable for correcting position bias. Affine correction (AC) is a generalization of IPS that corrects for position bias and trust bias. IPS and AC provably remove bias, conditioned on an accurate estimation of the bias parameters. Estimating the bias parameters, in turn, requires an accurate estimation of the relevance probabilities. This cyclic dependency introduces practical limitations in terms of sensitivity, convergence and efficiency. We propose a new correction method for position and trust bias in CLTR in which, unlike the existing methods, the correction does not rely on relevance estimation. Our proposed method, mixture-based correction (MBC), is based on the assumption that the distribution of the CTRs over the items being ranked is a mixture of two distributions: the distribution of CTRs for relevant items and the distribution of CTRs for non-relevant items. We prove that our method is unbiased. The validity of our proof is not conditioned on accurate bias parameter estimation. Our experiments show that MBC, when used in different bias settings and accompanied by different LTR algorithms, outperforms AC, the state-of-the-art method for correcting position and trust bias, in some settings, while performing on par in other settings. Furthermore, MBC is orders of magnitude more efficient than AC in terms of the training time.