arXiv subjects

Yu Meng

Publications and source records attributed to Yu Meng.

126 records · Page 7Linked to original sources

arXiv2020

CoRel: Seed-Guided Topical Taxonomy Construction by Concept Learning and Relation Transferring

Taxonomy is not only a fundamental form of knowledge representation, but also crucial to vast knowledge-rich applications, such as question answering and web search. Most existing taxonomy construction methods extract hypernym-hyponym entity pairs to organize a "universal" taxonomy. However, these generic taxonomies cannot satisfy user's specific interest in certain areas and relations. Moreover, the nature of instance taxonomy treats each node as a single word, which has low semantic coverage. In this paper, we propose a method for seed-guided topical taxonomy construction, which takes a corpus and a seed taxonomy described by concept names as input, and constructs a more complete taxonomy based on user's interest, wherein each node is represented by a cluster of coherent terms. Our framework, CoRel, has two modules to fulfill this goal. A relation transferring module learns and transfers the user's interested relation along multiple paths to expand the seed taxonomy structure in width and depth. A concept learning module enriches the semantics of each concept node by jointly embedding the taxonomy and text. Comprehensive experiments conducted on real-world datasets show that Corel generates high-quality topical taxonomies and outperforms all the baselines significantly.

cs.CL↗

arXiv2020

Ward Identity of the Vector Current and the Decay Rate of $η_c\rightarrowγγ$ in Lattice QCD

Using a recently proposed method arXiv:1910.11597 (Yu Meng et al.), we study the two-photon decay rate of $η_c$ using two $N_f=2$ twisted mass gauge ensembles with lattice spacings $0.067$fm and $0.085$fm. The results obtained from these two ensembles can be extrapolated in a naive fashion to the continuum limit, yielding a result that is consistent with the experimental one within two standard deviations. To be specific, we obtain the results for two-photon decay of $η_c$ as $\mathcal{B}(η_c\rightarrow 2γ)= 1.29(3)(18)\times 10^{-4}$ where the first error is statistical and the second is our estimate for the systematic error caused by the finite lattice spacing. It turns out that Ward identity for the vector current is of vital importance within this new method. We find that the Ward identity is violated for local current with a finite lattice spacing, however it will be restored after the continuum limit is taken.

hep-lat↗

arXiv2020

Hierarchical Topic Mining via Joint Spherical Tree and Text Embedding

Mining a set of meaningful topics organized into a hierarchy is intuitively appealing since topic correlations are ubiquitous in massive text corpora. To account for potential hierarchical topic structures, hierarchical topic models generalize flat topic models by incorporating latent topic hierarchies into their generative modeling process. However, due to their purely unsupervised nature, the learned topic hierarchy often deviates from users' particular needs or interests. To guide the hierarchical topic discovery process with minimal user supervision, we propose a new task, Hierarchical Topic Mining, which takes a category tree described by category names only, and aims to mine a set of representative terms for each category from a text corpus to help a user comprehend his/her interested topics. We develop a novel joint tree and text embedding method along with a principled optimization procedure that allows simultaneous modeling of the category tree structure and the corpus generative process in the spherical space for effective category-representative term discovery. Our comprehensive experiments show that our model, named JoSH, mines a high-quality set of hierarchical topics with high efficiency and benefits weakly-supervised hierarchical text classification tasks.

cs.CL↗

arXiv2020

A Lattice Study of the Two-photon Decay Widths for Scalar and Pseudo-scalar Charmonium

In this exploratory study, two photon decay widths of pseudo-scalar ($η_c$) and scalar ($χ_{c0}$) charmonium are computed using two ensembles of $N_f=2$ twisted mass lattice QCD gauge configurations. The simulation is performed two lattice ensembles with lattice spacings $a=0.067$ fm with size $32^3\times{64}$ and $a=0.085$ fm with size $24^3\times{48}$, respectively. The results for the decay widths for the two charmonia are obtained which are in the right ballpark however smaller than the experimental ones. Possible reasons for these discrepancies are discussed.

hep-lat↗

arXiv2020

Experimental observation of coherent-information superadditivity in a dephrasure channel

We present an experimental approach to construct a dephrasure channel, which contains both dephasing and erasure noises, and can be used as an efficient tool to study the superadditivity of coherent information. By using a three-fold dephrasure channel, the superadditivity of coherent information is observed, and a substantial gap is found between the zero single-letter coherent information and zero quantum capacity. Particularly, we find that when the coherent information of n channel uses is zero, in the case of larger number of channel uses, it will become positive. These phenomena exhibit a more obvious superadditivity of coherent information than previous works, and demonstrate a higher threshold for non-zero quantum capacity. Such novel channels built in our experiment also can provide a useful platform to study the non-additive properties of coherent information and quantum channel capacity.

quant-ph↗

arXiv2020

Three Photon Decay of $J/ψ$ from Lattice QCD

Three photon decay rate of $J/ψ$ is studied using two $N_f=2$ twisted mass gauge ensembles with lattice spacings $a\simeq 0.085$ fm (I) and $0.067$ fm(II). Using a new method, only the correlation functions directly related to the physical decay width are computed with all polarizations of the initial and final states summed over. Our results for such rare decay on the two ensembles are: $\mathcal{B}_{I,II}(J/ψ\rightarrow 3γ)=(1.614 \pm 0.016 \pm 0.261)\times 10^{-5},(1.809 \pm 0.051 \pm 0.295)\times 10^{-5}$ where the first errors are statistical and the second are estimates from systematics. We also propose a method to analyze the Dalitz plot of the corresponding process based on the lattice data which can provide direct information for the experiments.

hep-lat↗

arXiv2020

Discriminative Topic Mining via Category-Name Guided Text Embedding

Mining a set of meaningful and distinctive topics automatically from massive text corpora has broad applications. Existing topic models, however, typically work in a purely unsupervised way, which often generate topics that do not fit users' particular needs and yield suboptimal performance on downstream tasks. We propose a new task, discriminative topic mining, which leverages a set of user-provided category names to mine discriminative topics from text corpora. This new task not only helps a user understand clearly and distinctively the topics he/she is most interested in, but also benefits directly keyword-driven classification tasks. We develop CatE, a novel category-name guided text embedding method for discriminative topic mining, which effectively leverages minimal user guidance to learn a discriminative embedding space and discover category representative terms in an iterative manner. We conduct a comprehensive set of experiments to show that CatE mines high-quality set of topics guided by category names only, and benefits a variety of downstream applications including weakly-supervised classification and lexical entailment direction identification.

cs.CL↗

arXiv2020

Guiding Corpus-based Set Expansion by Auxiliary Sets Generation and Co-Expansion

Given a small set of seed entities (e.g., ``USA'', ``Russia''), corpus-based set expansion is to induce an extensive set of entities which share the same semantic class (Country in this example) from a given corpus. Set expansion benefits a wide range of downstream applications in knowledge discovery, such as web search, taxonomy construction, and query suggestion. Existing corpus-based set expansion algorithms typically bootstrap the given seeds by incorporating lexical patterns and distributional similarity. However, due to no negative sets provided explicitly, these methods suffer from semantic drift caused by expanding the seed set freely without guidance. We propose a new framework, Set-CoExpan, that automatically generates auxiliary sets as negative sets that are closely related to the target set of user's interest, and then performs multiple sets co-expansion that extracts discriminative features by comparing target set with auxiliary sets, to form multiple cohesive sets that are distinctive from one another, thus resolving the semantic drift issue. In this paper we demonstrate that by generating auxiliary sets, we can guide the expansion process of target set to avoid touching those ambiguous areas around the border with auxiliary sets, and we show that Set-CoExpan outperforms strong baseline methods significantly.

cs.CL↗

arXiv2019

Separate and Attend in Personal Email Search

In personal email search, user queries often impose different requirements on different aspects of the retrieved emails. For example, the query "my recent flight to the US" requires emails to be ranked based on both textual contents and recency of the email documents, while other queries such as "medical history" do not impose any constraints on the recency of the email. Recent deep learning-to-rank models for personal email search often directly concatenate dense numerical features (e.g., document age) with embedded sparse features (e.g., n-gram embeddings). In this paper, we first show with a set of experiments on synthetic datasets that direct concatenation of dense and sparse features does not lead to the optimal search performance of deep neural ranking models. To effectively incorporate both sparse and dense email features into personal email search ranking, we propose a novel neural model, SepAttn. SepAttn first builds two separate neural models to learn from sparse and dense features respectively, and then applies an attention mechanism at the prediction level to derive the final prediction from these two models. We conduct a comprehensive set of experiments on a large-scale email search dataset, and demonstrate that our SepAttn model consistently improves the search quality over the baseline models.

cs.IR↗

arXiv2019

Spherical Text Embedding

Unsupervised text embedding has shown great power in a wide range of NLP tasks. While text embeddings are typically learned in the Euclidean space, directional similarity is often more effective in tasks such as word similarity and document clustering, which creates a gap between the training stage and usage stage of text embedding. To close this gap, we propose a spherical generative model based on which unsupervised word and paragraph embeddings are jointly learned. To learn text embeddings in the spherical space, we develop an efficient optimization algorithm with convergence guarantee based on Riemannian optimization. Our model enjoys high efficiency and achieves state-of-the-art performances on various text embedding tasks including word similarity and document clustering.

cs.CL↗

arXiv2019

Through-Wall Pose Imaging in Real-Time with a Many-to-Many Encoder/Decoder Paradigm

Overcoming the visual barrier and developing "see-through vision" has been one of mankind's long-standing dreams. Unlike visible light, Radio Frequency (RF) signals penetrate opaque obstructions and reflect highly off humans. This paper establishes a deep-learning model that can be trained to reconstruct continuous video of a 15-point human skeleton even through visual occlusion. The training process adopts a student/teacher learning procedure inspired by the Feynman learning technique, in which video frames and RF data are first collected simultaneously using a co-located setup containing an optical camera and an RF antenna array transceiver. Next, the video frames are processed with a computer-vision-based gait analysis "teacher" module to generate ground-truth human skeletons for each frame. Then, the same type of skeleton is predicted from corresponding RF data using a "student" deep-learning model consisting of a Residual Convolutional Neural Network (CNN), Region Proposal Network (RPN), and Recurrent Neural Network with Long-Short Term Memory (LSTM) that 1) extracts spatial features from RF images, 2) detects all people present in a scene, and 3) aggregates information over many time-steps, respectively. The model is shown to both accurately and completely predict the pose of humans behind visual obstruction solely using RF signals. Primary academic contributions include the novel many-to-many imaging methodology, unique integration of RPN and LSTM networks, and original training pipeline.

cs.CV↗

arXiv2019

A Data-Center FPGA Acceleration Platform for Convolutional Neural Networks

Intensive computation is entering data centers with multiple workloads of deep learning. To balance the compute efficiency, performance, and total cost of ownership (TCO), the use of a field-programmable gate array (FPGA) with reconfigurable logic provides an acceptable acceleration capacity and is compatible with diverse computation-sensitive tasks in the cloud. In this paper, we develop an FPGA acceleration platform that leverages a unified framework architecture for general-purpose convolutional neural network (CNN) inference acceleration at a data center. To overcome the computation bound, 4,096 DSPs are assembled and shaped as supertile units (SUs) for different types of convolution, which provide up to 4.2 TOP/s 16-bit fixed-point performance at 500 MHz. The interleaved-task-dispatching method is proposed to map the computation across the SUs, and the memory bound is solved by a dispatching-assembling buffering model and broadcast caches. For various non-convolution operators, a filter processing unit is designed for general-purpose filter-like/pointwise operators. In the experiment, the performances of CNN models running on server-class CPUs, a GPU, and an FPGA are compared. The results show that our design achieves the best FPGA peak performance and a throughput at the same level as that of the state-of-the-art GPU in data centers, with more than 50 times lower latency.

cs.CV↗

arXiv2019

Reconstruction of a Photonic Qubit State with Reinforcement Learning

An experiment is performed to reconstruct an unknown photonic quantum state with a limited amount of copies. A semi-quantum reinforcement learning approach is employed to adapt one qubit state, an "agent," to an unknown quantum state, an "environment," by successive single-shot measurements and feedback, in order to achieve maximum overlap. The experimental learning device herein, composed of a quantum photonics setup, can adjust the corresponding parameters to rotate the agent system based on the measurement outcomes "0" or "1" in the environment (i.e., reward/punishment signals). The results show that, when assisted by such a quantum machine learning technique, fidelities of the deterministic single-photon agent states can achieve over 88% under a proper reward/punishment ratio within 50 iterations. This protocol offers a tool for reconstructing an unknown quantum state when only limited copies are provided, and can also be extended to higher dimensions, multipartite, and mixed quantum state scenarios.

quant-ph↗

arXiv2018

Weakly-Supervised Hierarchical Text Classification

Hierarchical text classification, which aims to classify text documents into a given hierarchy, is an important task in many real-world applications. Recently, deep neural models are gaining increasing popularity for text classification due to their expressive power and minimum requirement for feature engineering. However, applying deep neural networks for hierarchical text classification remains challenging, because they heavily rely on a large amount of training data and meanwhile cannot easily determine appropriate levels of documents in the hierarchical setting. In this paper, we propose a weakly-supervised neural method for hierarchical text classification. Our method does not require a large amount of training data but requires only easy-to-provide weak supervision signals such as a few class-related documents or keywords. Our method effectively leverages such weak supervision signals to generate pseudo documents for model pre-training, and then performs self-training on real unlabeled data to iteratively refine the model. During the training process, our model features a hierarchical neural structure, which mimics the given hierarchy and is capable of determining the proper levels for documents with a blocking mechanism. Experiments on three datasets from different domains demonstrate the efficacy of our method compared with a comprehensive set of baselines.

cs.CL↗

arXiv2018

Weakly-Supervised Neural Text Classification

Deep neural networks are gaining increasing popularity for the classic text classification task, due to their strong expressive power and less requirement for feature engineering. Despite such attractiveness, neural text classification models suffer from the lack of training data in many real-world applications. Although many semi-supervised and weakly-supervised text classification models exist, they cannot be easily applied to deep neural models and meanwhile support limited supervision types. In this paper, we propose a weakly-supervised method that addresses the lack of training data in neural text classification. Our method consists of two modules: (1) a pseudo-document generator that leverages seed information to generate pseudo-labeled documents for model pre-training, and (2) a self-training module that bootstraps on real unlabeled data for model refinement. Our method has the flexibility to handle different types of weak supervision and can be easily integrated into existing deep neural models for text classification. We have performed extensive experiments on three real-world datasets from different domains. The results demonstrate that our proposed method achieves inspiring performance without requiring excessive training data and outperforms baseline methods significantly.

cs.IR↗

arXiv2018

Three-particle bound states in a finite volume: unequal masses and higher partial waves

An explicit expression for the finite-volume energy shift of shallow three-body bound states for non-identical particles is obtained in the unitary limit. The inclusion of the higher partial waves is considered. To this end, the method of arXiv:1412.4969 (Meißner et al.) is generalized for the case of unequal masses and arbitrary angular momenta. It is shown that in the S-wave and in the equal mass limit, the result from arXiv:1412.4969 is reproduced.

hep-lat↗

arXiv2018

Monocular Vision-based Vehicle Localization Aided by Fine-grained Classification

Monocular camera systems are prevailing in intelligent transportation systems, but by far they have rarely been used for dimensional purposes such as to accurately estimate the localization information of a vehicle. In this paper, we show that this capability can be realized. By integrating a series of advanced computer vision techniques including foreground extraction, edge and line detection, etc., and by utilizing deep learning networks for fine-grained vehicle model classification, we developed an algorithm which can estimate vehicles location (position, orientation and boundaries) within the environment down to 3.79 percent position accuracy and 2.5 degrees orientation accuracy. With this enhancement, current massive surveillance camera systems can potentially play the role of e-traffic police and trigger many new intelligent transportation applications, for example, to guide vehicles for parking or even for autonomous driving.

cs.RO↗

arXiv2018

Verifying nonlinear analog and mixed-signal circuits with inputs

We present a new technique for verifying nonlinear and hybrid models with inputs. We observe that once an input signal is fixed, the sensitivity analysis of the model can be computed much more precisely. Based on this result, we propose a new simulation-driven verification algorithm and apply it to a suite of nonlinear and hybrid models of CMOS digital circuits under different input signals. The models are low-dimensional but with highly nonlinear ODEs, with nearly hundreds of logarithmic and exponential terms. Some of our experiments analyze the metastability of bistable circuits with very sensitive ODEs and rigorously establish the connection between metastability recovery time and sensitivity.

eess.SY↗