When humans write, they may unintentionally omit some information. Complementing the omitted information using a computer is helpful in providing writing support. Recently, in the field of story understanding and generation, story completion (SC) was proposed to generate the missing parts of an incomplete story. Although its applicability is limited because it requires that the user have prior knowledge of the missing part of a story, missing position prediction (MPP) can be used to compensate for this problem. MPP aims to predict the position of the missing part, but the prerequisite knowledge that "one sentence is missing" is still required. In this study, we propose Variable Number MPP (VN-MPP), a new MPP task that removes this restriction; that is, the task to predict multiple missing sentences or to judge whether there are no missing sentences in the first place. We also propose two methods for this new MPP task. Furthermore, based on the novel task and methods, we developed a creative writing support system, COMPASS. The results of a user experiment involving professional creators who write texts in Japanese confirm the efficacy and utility of the developed system.
Multi-image super-resolution, which aims to fuse and restore a high-resolution image from multiple images at the same location, is crucial for utilizing satellite images. The satellite images are often occluded by atmospheric disturbances such as clouds, and the position of the disturbances varies by the images. Many radiometric and geometric approaches are proposed to detect atmospheric disturbances. Still, the utilization of detection results, i.e., quality maps in deep learning was limited to pre-processing or computation of loss. In this paper, we present a quality map-associated attention network (QA-Net), an architecture that fully incorporates QMs into a deep learning scheme for the first time. Our proposed attention modules process QMs alongside the low-resolution images and utilize the QM features to distinguish the disturbances and attend to image features. As a result, QA-Net has achieved state-of-the-art results in the PROBA-V dataset.
Goal-conditioned reinforcement learning is a crucial yet challenging algorithm which enables agents to achieve multiple user-specified goals when learning a set of skills in a dynamic environment. However, it typically requires millions of the environmental interactions explored by agents, which is sample-inefficient. In the paper, we propose a skill learning framework DR-GRL that aims to improve the sample efficiency and policy generalization by combining the Disentangled Representation learning and Goal-conditioned visual Reinforcement Learning. In a weakly supervised manner, we propose a Spatial Transform AutoEncoder (STAE) to learn an interpretable and controllable representation in which different parts correspond to different object attributes (shape, color, position). Due to the high controllability of the representations, STAE can simply recombine and recode the representations to generate unseen goals for agents to practice themselves. The manifold structure of the learned representation maintains consistency with the physical position, which is beneficial for reward calculation. We empirically demonstrate that DR-GRL significantly outperforms the previous methods in sample efficiency and policy generalization. In addition, DR-GRL is also easy to expand to the real robot.
Most instance segmentation models are not end-to-end trainable due to either the incorporation of proposal estimation (RPN) as a pre-processing or non-maximum suppression (NMS) as a post-processing. Here we propose a novel end-to-end instance segmentation method termed ISDA. It reshapes the task into predicting a set of object masks, which are generated via traditional convolution operation with learned position-aware kernels and features of objects. Such kernels and features are learned by leveraging a deformable attention network with multi-scale representation. Thanks to the introduced set-prediction mechanism, the proposed method is NMS-free. Empirically, ISDA outperforms Mask R-CNN (the strong baseline) by 2.6 points on MS-COCO, and achieves leading performance compared with recent models. Code will be available soon.
In this position paper, we describe our perspective on how meaningful resources for lower-resourced languages should be developed in connection with the speakers of those languages. We first examine two massively multilingual resources in detail. We explore the contents of the names stored in Wikidata for a few lower-resourced languages and find that many of them are not in fact in the languages they claim to be and require non-trivial effort to correct. We discuss quality issues present in WikiAnn and evaluate whether it is a useful supplement to hand annotated data. We then discuss the importance of creating annotation for lower-resourced languages in a thoughtful and ethical way that includes the languages' speakers as part of the development process. We conclude with recommended guidelines for resource development.
Reconfigurable intelligent surfaces (RISs) are one of the most promising technological enablers of the next (6th) generation of wireless systems. In this paper, we introduce a novel use-case of the RIS technology in radio localization, which is enabling the user to estimate its own position via transmitting orthogonal frequency-division multiplexing (OFDM) pilots and processing the signal reflected from the RIS. We demonstrate that user localization in this scenario is possible by deriving Cramer-Rao lower bounds on the positioning error and devising a low-complexity position estimation algorithm. We consider random and directional RIS phase profiles and apply a specific temporal coding to them, such that the reflected signal from the RIS can be separated from the uncontrolled multipath. Finally, we assess the performance of our position estimator for an example system and show that the proposed algorithm can attain the derived bound at high signal-to-noise ratio values.
This paper proposes a fast eye detection method that is based on a Siamese network for near infrared (NIR) partial face images. NIR partial face images do not include the whole face of a subject since they are captured using iris recognition systems with the constraint of frame rate and resolution. The iris recognition systems such as the iris on the move (IOTM) system require fast and accurate eye detection as a pre-process. Our goal is to design eye detection with high speed, high discrimination performance between left and right eyes, and high positional accuracy of eye center. Our method adopts a Siamese network and coarse to fine position estimation with a fast lightweight CNN backbone. The network outputs features of images and the similarity map indicating coarse position of an eye. A regression on a portion of a feature with high similarity refines the coarse position of the eye to obtain the fine position with high accuracy. We demonstrate the effectiveness of the proposed method by comparing it with conventional methods, including SOTA, in terms of the positional accuracy, the discrimination performance, and the processing speed. Our method achieves superior performance in speed.
Research on infectious diseases constitutes a transversal scientific field. A specific corpus is designed by combining a controlled language (Medline MeSH thesaurus) and the categorization of journals (Web of Science). From this global corpus, the article characterizes the publications from the top 20 countries publishing in the field and evolutions between 2000 and 2020. Topic maps show the research themes within the field of infectious diseases both in the world and in France. The explosion of publications on Covid-19 in 2020 has a quite visible impact on the topic map in infectious diseases and changes the position of some countries in this field of research. The conclusion points to issues for further research as more complete data will become available on the Covid-19 period.
Given a multi-agent linear system, we formalize and solve a trajectory optimization problem that encapsulates trajectory tracking, distance-based formation control and input energy minimization. To this end, a numerical projection operator Newton's method is developed to find a solution by the minimization of a cost functional able to capture all these different tasks. To stabilize the formation, a particular potential function has been designed, allowing to obtain specified geometrical configurations while the barycenter position and velocity of the system follows a desired trajectory.
To achieve point cloud denoising, traditional methods heavily rely on geometric priors, and most learning-based approaches suffer from outliers and loss of details. Recently, the gradient-based method was proposed to estimate the gradient fields from the noisy point clouds using neural networks, and refine the position of each point according to the estimated gradient. However, the predicted gradient could fluctuate, leading to perturbed and unstable solutions, as well as a long inference time. To address these issues, we develop the momentum gradient ascent method that leverages the information of previous iterations in determining the trajectories of the points, thus improving the stability of the solution and reducing the inference time. Experiments demonstrate that the proposed method outperforms state-of-the-art approaches with a variety of point clouds, noise types, and noise levels. Code is available at: https://github.com/IndigoPurple/MAG
Combining image sensor simulation tools (e.g., ISETCam) with physically based ray tracing (e.g., PBRT) offers possibilities for designing and evaluating novel imaging systems as well as for synthesizing physically accurate, labeled images for machine learning. One practical limitation has been simulating the optics precisely: Lens manufacturers generally prefer to keep lens design confidential. We present a pragmatic solution to this problem using a black box lens model in Zemax; such models provide necessary optical information while preserving the lens designer's intellectual property. First, we describe and provide software to construct a polynomial ray transfer function that characterizes how rays entering the lens at any position and angle subsequently exit the lens. We implement the ray-transfer calculation as a camera model in PBRT and confirm that the PBRT ray-transfer calculations match the Zemax lens calculations for edge spread functions and relative illumination.
In this position paper, we study interactive learning for structured output spaces, with a focus on active learning, in which labels are unknown and must be acquired, and on skeptical learning, in which the labels are noisy and may need relabeling. These scenarios require expressive models that guarantee reliable and efficient computation of probabilistic quantities to measure uncertainty. We identify conditions under which a class of probabilistic models -- which we denote CRISPs -- meet all of these conditions, thus delivering tractable computation of the above quantities while preserving expressiveness. Building on prior work on tractable probabilistic circuits, we illustrate how CRISPs enable robust and efficient active and skeptical learning in large structured output spaces.
Source code summarization aims at generating concise and clear natural language descriptions for programming languages. Well-written code summaries are beneficial for programmers to participate in the software development and maintenance process. To learn the semantic representations of source code, recent efforts focus on incorporating the syntax structure of code into neural networks such as Transformer. Such Transformer-based approaches can better capture the long-range dependencies than other neural networks including Recurrent Neural Networks (RNNs), however, most of them do not consider the structural relative correlations between tokens, e.g., relative positions in Abstract Syntax Trees (ASTs), which is beneficial for code semantics learning. To model the structural dependency, we propose a Structural Relative Position guided Transformer, named SCRIPT. SCRIPT first obtains the structural relative positions between tokens via parsing the ASTs of source code, and then passes them into two types of Transformer encoders. One Transformer directly adjusts the input according to the structural relative distance; and the other Transformer encodes the structural relative positions during computing the self-attention scores. Finally, we stack these two types of Transformer encoders to learn representations of source code. Experimental results show that the proposed SCRIPT outperforms the state-of-the-art methods by at least 1.6%, 1.4% and 2.8% with respect to BLEU, ROUGE-L and METEOR on benchmark datasets, respectively. We further show that how the proposed SCRIPT captures the structural relative dependencies.
Multi-document summarization is more challenging than single-document summarization since it has to solve the problem of overlapping information among sentences from different documents. Also, since multi-document summarization dataset is rare, methods based on deep learning are difficult to be applied. In this paper, we propose an approach to multi-document summarization based on a k-means clustering algorithm, combining with the centroid-based method, maximal marginal relevance, and sentence positions. This approach is efficient in finding salient sentences and preventing overlapping between sentences. Experiments using DUC 2007 dataset show that our system is more efficient than other researchers in this field.
One critical component in lossy deep image compression is the entropy model, which predicts the probability distribution of the quantized latent representation in the encoding and decoding modules. Previous works build entropy models upon convolutional neural networks which are inefficient in capturing global dependencies. In this work, we propose a novel transformer-based entropy model, termed Entroformer, to capture long-range dependencies in probability distribution estimation effectively and efficiently. Different from vision transformers in image classification, the Entroformer is highly optimized for image compression, including a top-k self-attention and a diamond relative position encoding. Meanwhile, we further expand this architecture with a parallel bidirectional context model to speed up the decoding process. The experiments show that the Entroformer achieves state-of-the-art performance on image compression while being time-efficient.
Taxonomies are fundamental to many real-world applications in various domains, serving as structural representations of knowledge. To deal with the increasing volume of new concepts needed to be organized as taxonomies, researchers turn to automatically completion of an existing taxonomy with new concepts. In this paper, we propose TaxoEnrich, a new taxonomy completion framework, which effectively leverages both semantic features and structural information in the existing taxonomy and offers a better representation of candidate position to boost the performance of taxonomy completion. Specifically, TaxoEnrich consists of four components: (1) taxonomy-contextualized embedding which incorporates both semantic meanings of concept and taxonomic relations based on powerful pretrained language models; (2) a taxonomy-aware sequential encoder which learns candidate position representations by encoding the structural information of taxonomy; (3) a query-aware sibling encoder which adaptively aggregates candidate siblings to augment candidate position representations based on their importance to the query-position matching; (4) a query-position matching model which extends existing work with our new candidate position representations. Extensive experiments on four large real-world datasets from different domains show that \TaxoEnrich achieves the best performance among all evaluation metrics and outperforms previous state-of-the-art methods by a large margin.
Bearingless motors use a single stator assembly to apply torque and magnetic suspension forces on the rotor, making these machines compact with frictionless operation and thus well suited to high-speed applications. One major challenge that prevents wide usage of bearingless motors is the need for air-gap position sensors, which are typically expensive. Here we present a method to estimate the radial position of a hysteresis-type bearingless motor using the inductance variation of the stator coils amplified by an injected high-frequency signal. We have carried out finite element (FE) simulations to demonstrate its feasibility, and have constructed a prototype self-sensing bearingless motor for experimental validations.
Aiming for a higher economic efficiency in manufacturing, an increased degree of automation is a key enabler. However, assessing the technical feasibility of an automated assembly solution for a dedicated process is difficult and often determined by the geometry of the given product parts. Among others, decisive criterions of the automation feasibility are the ability to separate and isolate single parts or the capability of component self-alignment in final position. To assess the feasibility, a questionnaire based evaluation scheme has been developed and applied by Fraunhofer researchers. However, the results strongly depend on the implicit knowledge and experience of the single engineer performing the assessment. This paper presents NeuroCAD, a software tool that automates the assessment using voxelization techniques. The approach enables the assessment of abstract and production relevant geometries features through deep-learning based on CAD files.
How is knowledge of position-role mappings in natural language learned? We explore this question in a computational setting, testing whether a variety of well-performing pertained language models (BERT, RoBERTa, and DistilBERT) exhibit knowledge of these mappings, and whether this knowledge persists across alternations in syntactic, structural, and lexical alternations. In Experiment 1, we show that these neural models do indeed recognize distinctions between theme and recipient roles in ditransitive constructions, and that these distinct patterns are shared across construction type. We strengthen this finding in Experiment 2 by showing that fine-tuning these language models on novel theme- and recipient-like tokens in one paradigm allows the models to make correct predictions about their placement in other paradigms, suggesting that the knowledge of these mappings is shared rather than independently learned. We do, however, observe some limitations of this generalization when tasks involve constructions with novel ditransitive verbs, hinting at a degree of lexical specificity which underlies model performance.
The word mover's distance (WMD) is a popular semantic similarity metric for two texts. This position paper studies several possible extensions of WMD. We experiment with the frequency of words in the corpus as a weighting factor and the geometry of the word vector space. We validate possible extensions of WMD on six document classification datasets. Some proposed extensions show better results in terms of the k-nearest neighbor classification error than WMD.