The notion of word embedding plays a fundamental role in natural language processing (NLP). However, pre-training word embedding for very large-scale vocabulary is computationally challenging for most existing methods. In this work, we show that with
merely a small fraction of contexts (Q-contexts)which are typical in the whole corpus (and their mutual information with words), one can construct high-quality word embedding with negligible errors. Mutual information between contexts and words can be encoded canonically as a sampling state, thus, Q-contexts can be fast constructed. Furthermore, we present an efficient and effective WEQ method, which is capable of extracting word embedding directly from these typical contexts. In practical scenarios, our algorithm runs 11$sim$13 times faster than well-established methods. By comparing with well-known methods such as matrix factorization, word2vec, GloVeand fasttext, we demonstrate that our method achieves comparable performance on a variety of downstream NLP tasks, and in the meanwhile maintains run-time and resource advantages over all these baselines.
We study the possibility of measuring neutrino Yukawa couplings in the Next-to-Minimal Supersymmetric Standard Model with right-handed neutrinos (NMSSMr) when the lightest right-handed sneutrino is the Dark Matter (DM) candidate, by exploiting a `dij
et + dilepton + Missing Transverse Energy signature. We show that, contrary to the miminal realisation of Supersymmetry (SUSY), the MSSM, wherein the DM candidate is typically a much heavier (fermionic) neutralino state, this extended model of SUSY offers one with a much lighter (bosonic) state as DM that can then be produced at the next generation of $e^+e^-$ colliders with energies up to 500 GeV or so. The ensuing signal, energing from chargino pair production and subsequent decay, is extremely pure so it also affords one with the possibility of extracting the Yukawa parameters of the (s)neutrino sector. Altogether, our results serve the purpose of motivating searches for light DM signals at such machines, where the DM candidate can have a mass around the electroweak scale.
Unsupervised domain adaptation aims to train a model from the labeled source domain to make predictions on the unlabeled target domain when the data distribution of the two domains is different. As a result, it needs to reduce the data distribution d
ifference between the two domains to improve the models generalization ability. Existing methods tend to align the two domains directly at the domain-level, or perform class-level domain alignment based on deep feature. The former ignores the relationship between the various classes in the two domains, which may cause serious negative transfer, the latter alleviates it by introducing pseudo-labels of the target domain, but it does not consider the importance of performing class-level alignment on shallow feature representations. In this paper, we develop this work on the method of class-level alignment. The proposed method reduces the difference between two domains dramaticlly by aligning multi-level features. In the case that the two domains share the label space, the class-level alignment is implemented by introducing Multi-Level Feature Contrastive Networks (MLFCNet). In practice, since the categories of samples in target domain are unavailable, we iteratively use clustering algorithm to obtain the pseudo-labels, and then minimize Multi-Level Contrastive Discrepancy (MLCD) loss to achieve more accurate class-level alignment. Experiments on three real-world benchmarks ImageCLEF-DA, Office-31 and Office-Home demonstrate that MLFCNet compares favorably against the existing state-of-the-art domain adaptation methods.
Phase retrieval aims at reconstructing unknown signals from magnitude measurements of linear mixtures. In this paper, we consider the phase retrieval with dictionary learning problem, which includes an additional prior information that the measured s
ignal admits a sparse representation over an unknown dictionary. The task is to jointly estimate the dictionary and the sparse representation from magnitude-only measurements. To this end, we study two complementary formulations and propose efficient parallel algorithms based on the successive convex approximation framework. The first algorithm is termed compact-SCAphase and is preferable in the case of less diverse mixture models. It employs a compact formulation that avoids the use of auxiliary variables. The proposed algorithm is highly scalable and has reduced parameter tuning cost. The second algorithm, referred to as SCAphase, uses auxiliary variables and is favorable in the case of highly diverse mixture models. It also renders simple incorporation of additional side constraints. The performance of both methods is evaluated when applied to blind sparse channel estimation from subband magnitude measurements in a multi-antenna random access network. Simulation results demonstrate the efficiency of the proposed techniques compared to state-of-the-art methods.
The textit{Multi-Constraint Shortest Path (MCSP)} problem aims to find the shortest path between two nodes in a network subject to a given constraint set. It is typically processed as a textit{skyline path} problem. However, the number of intermediat
e skyline paths becomes larger as the network size increases and the constraint number grows, which brings about the dramatical growth of computational cost and further makes the existing index-based methods hardly capable of obtaining the complete exact results. In this paper, we propose a novel high-dimensional skyline path concatenation method to avoid the expensive skyline path search, which then supports the efficient construction of hop labeling index for textit{MCSP} queries. Specifically, a set of insightful observations and techniques are proposed to improve the efficiency of concatenating two skyline path set, a textit{n-Cube} technique is designed to prune the concatenation space among multiple hops, and a textit{constraint pruning} method is used to avoid the unnecessary computation. Furthermore, to scale up to larger networks, we propose a novel textit{forest hop labeling} which enables the parallel label construction from different network partitions. Our approach is the first method that can achieve both accuracy and efficiency for textit{MCSP} query answering. Extensive experiments on real-life road networks demonstrate the superiority of our method over the state-of-the-art solutions.
Sarcasm employs ambivalence, where one says something positive but actually means negative, and vice versa. Due to the sophisticated and obscure sentiment, sarcasm brings in great challenges to sentiment analysis. In this paper, we show up the essenc
e of sarcastic text is that the literal sentiment (expressed by the surface form of the text) is opposite to the deep sentiment (expressed by the actual meaning of the text). To this end, we propose a Dual-Channel Framework by modeling both literal and deep sentiments to recognize the sentiment conflict. Specifically, the proposed framework is capable of detecting the sentiment conflict between the literal and deep meanings of the input text. Experiments on the political debates and the Twitter datasets show that our framework achieves the best performance on sarcasm recognition.
The evolution analysis on Web service ecosystems has become a critical problem as the frequency of service changes on the Internet increases rapidly. Developers need to understand these evolution patterns to assist in their decision-making on service
selection. ProgrammableWeb is a popular Web service ecosystem on which several evolution analyses have been conducted in the literature. However, the existing studies have ignored the quality issues of the ProgrammableWeb dataset and the issue of service obsolescence. In this study, we first report the quality issues identified in the ProgrammableWeb dataset from our empirical study. Then, we propose a novel method to correct the relevant evolution analysis data by estimating the life cycle of application programming interfaces (APIs) and mashups. We also reveal how to use three different dynamic network models in the service ecosystem evolution analysis based on the corrected ProgrammableWeb dataset. Our experimental experience iterates the quality issues of the original ProgrammableWeb and highlights several research opportunities.
The recently observed two and four-quasiparticle high-spin rotational bands in the odd-odd nuclei $^{166, 168, 170, 172}$Re are investigated using the cranked shell model with pairing correlations treated by a particle-number conserving method. The e
xperimental moments of inertia and alignments can be reproduced well by the present calculation if appropriate bandhead spins and configurations are assigned for these bands, which in turn confirms their spin and configuration assignments. It is found that the bandhead spins of those two rotational bands observed in $^{166}$Re~[Li {it et al.}, Phys. Rev. C 92 014310 (2015)] should be both increased by $2hbar$ to get in consistent with the systematics of the experimental and calculated moments of inertia for the same configurations in $^{168, 170, 172}$Re. The variations of the backbendings/upbendings with increasing neutron number in these nuclei are investigated. The level crossing mechanism is well understood by analysing the variations of the occupation probabilities of the single-particle states close to the Fermi surface and their contributions to the angular momentum alignment with rotational frequency. In addition, the influence of the deformation driving effects of the proton $1/2^-[541]$ ($h_{9/2}$) orbtial on the level crossing in $^{172}$Re is also discussed.
Medical imaging technologies, including computed tomography (CT) or chest X-Ray (CXR), are largely employed to facilitate the diagnosis of the COVID-19. Since manual report writing is usually too time-consuming, a more intelligent auxiliary medical s
ystem that could generate medical reports automatically and immediately is urgently needed. In this article, we propose to use the medical visual language BERT (Medical-VLBERT) model to identify the abnormality on the COVID-19 scans and generate the medical report automatically based on the detected lesion regions. To produce more accurate medical reports and minimize the visual-and-linguistic differences, this model adopts an alternate learning strategy with two procedures that are knowledge pretraining and transferring. To be more precise, the knowledge pretraining procedure is to memorize the knowledge from medical texts, while the transferring procedure is to utilize the acquired knowledge for professional medical sentences generations through observations of medical images. In practice, for automatic medical report generation on the COVID-19 cases, we constructed a dataset of 368 medical findings in Chinese and 1104 chest CT scans from The First Affiliated Hospital of Jinan University, Guangzhou, China, and The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, China. Besides, to alleviate the insufficiency of the COVID-19 training samples, our model was first trained on the large-scale Chinese CX-CHR dataset and then transferred to the COVID-19 CT dataset for further fine-tuning. The experimental results showed that Medical-VLBERT achieved state-of-the-art performances on terminology prediction and report generation with the Chinese COVID-19 CT dataset and the CX-CHR dataset. The Chinese COVID-19 CT dataset is available at https://covid19ct.github.io/.
Salient object detection is the pixel-level dense prediction task which can highlight the prominent object in the scene. Recently U-Net framework is widely used, and continuous convolution and pooling operations generate multi-level features which ar
e complementary with each other. In view of the more contribution of high-level features for the performance, we propose a triplet transformer embedding module to enhance them by learning long-range dependencies across layers. It is the first to use three transformer encoders with shared weights to enhance multi-level features. By further designing scale adjustment module to process the input, devising three-stream decoder to process the output and attaching depth features to color features for the multi-modal fusion, the proposed triplet transformer embedding network (TriTransNet) achieves the state-of-the-art performance in RGB-D salient object detection, and pushes the performance to a new level. Experimental results demonstrate the effectiveness of the proposed modules and the competition of TriTransNet.
