arXiv subjects

Min Yang

Publications and source records attributed to Min Yang.

At least 325 records · Page 18Linked to original sources

arXiv2019

A Fast deflation Method for Sparse Principal Component Analysis via Subspace Projections

The implementation of conventional sparse principal component analysis (SPCA) on high-dimensional data sets has become a time consuming work. In this paper, a series of subspace projections are constructed efficiently by using Household QR factorization. With the aid of these subspace projections, a fast deflation method, called SPCA-SP, is developed for SPCA. This method keeps a good tradeoff between various criteria, including sparsity, orthogonality, explained variance, balance of sparsity, and computational cost. Comparative experiments on the benchmark data sets confirm the effectiveness of the proposed method.

stat.ML↗

arXiv2019

Joint Learning of Answer Selection and Answer Summary Generation in Community Question Answering

Community question answering (CQA) gains increasing popularity in both academy and industry recently. However, the redundancy and lengthiness issues of crowdsourced answers limit the performance of answer selection and lead to reading difficulties and misunderstandings for community users. To solve these problems, we tackle the tasks of answer selection and answer summary generation in CQA with a novel joint learning model. Specifically, we design a question-driven pointer-generator network, which exploits the correlation information between question-answer pairs to aid in attending the essential information when generating answer summaries. Meanwhile, we leverage the answer summaries to alleviate noise in original lengthy answers when ranking the relevancy degrees of question-answer pairs. In addition, we construct a new large-scale CQA corpus, WikiHowQA, which contains long answers for answer selection as well as reference summaries for answer summarization. The experimental results show that the joint learning method can effectively address the answer redundancy issue in CQA and achieves state-of-the-art results on both answer selection and text summarization tasks. Furthermore, the proposed model is shown to be of great transferring ability and applicability for resource-poor CQA tasks, which lack of reference answer summaries.

cs.CL↗

arXiv2019

Exciton valley depolarization in monolayer transition-metal dichalcogenides

The valley degree of freedom is a sought-after quantum number in monolayer transition-metal dichalcogenides. Similar to optical spin orientation in semiconductors, the helicity of absorbed photons can be relayed to the valley (pseudospin) quantum number of photoexcited electrons and holes. Also similar to the quantum-mechanical spin, the valley quantum number is not a conserved quantity. Valley depolarization of excitons in monolayer transition-metal dichalcogenides due to long-range electron-hole exchange typically takes a few ps at low temperatures. Exceptions to this behavior are monolayers MoSe$_2$ and MoTe$_2$ wherein the depolarization is much faster. We elucidate the enigmatic anomaly of these materials, finding that it originates from Rashba-induced coupling of the dark and bright exciton branches next to their degeneracy point. When photoexcited excitons scatter during their energy relaxation between states next to the degeneracy region, they reach the light cone after losing the initial helicity. The valley depolarization is not as fast in monolayers WSe$_2$, WS$_2$ and likely MoS$_2$ wherein the Rashba-induced coupling is negligible.

cond-mat.mes-hall↗

arXiv2019

MedTruth: A Semi-supervised Approach to Discovering Knowledge Condition Information from Multi-Source Medical Data

Knowledge Graph (KG) contains entities and the relations between entities. Due to its representation ability, KG has been successfully applied to support many medical/healthcare tasks. However, in the medical domain, knowledge holds under certain conditions. For example, symptom \emph{runny nose} highly indicates the existence of disease \emph{whooping cough} when the patient is a baby rather than the people at other ages. Such conditions for medical knowledge are crucial for decision-making in various medical applications, which is missing in existing medical KGs. In this paper, we aim to discovery medical knowledge conditions from texts to enrich KGs. Electronic Medical Records (EMRs) are systematized collection of clinical data and contain detailed information about patients, thus EMRs can be a good resource to discover medical knowledge conditions. Unfortunately, the amount of available EMRs is limited due to reasons such as regularization. Meanwhile, a large amount of medical question answering (QA) data is available, which can greatly help the studied task. However, the quality of medical QA data is quite diverse, which may degrade the quality of the discovered medical knowledge conditions. In the light of these challenges, we propose a new truth discovery method, MedTruth, for medical knowledge condition discovery, which incorporates prior source quality information into the source reliability estimation procedure, and also utilizes the knowledge triple information for trustworthy information computation. We conduct series of experiments on real-world medical datasets to demonstrate that the proposed method can discover meaningful and accurate conditions for medical knowledge by leveraging both EMR and QA data. Further, the proposed method is tested on synthetic datasets to validate its effectiveness under various scenarios.

cs.DB↗

arXiv2019

Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications

Obstacles hindering the development of capsule networks for challenging NLP applications include poor scalability to large output spaces and less reliable routing processes. In this paper, we introduce: 1) an agreement score to evaluate the performance of routing processes at instance level; 2) an adaptive optimizer to enhance the reliability of routing; 3) capsule compression and partial routing to improve the scalability of capsule networks. We validate our approach on two NLP tasks, namely: multi-label text classification and question answering. Experimental results show that our approach considerably improves over strong competitors on both tasks. In addition, we gain the best results in low-resource settings with few training instances.

cs.CL↗

arXiv2019

Coupled Decorated Membrane Resonators with Large Willis Coupling

We report the experimental studies on an acoustic scatterer consisting of a pair of coupled decorated membrane resonators (DMRs) that exhibits near extreme contrast in reflection asymmetry and strong Willis coupling coefficient with amplitude of 2.5 and polarizability cross term of 1.1 x 10-8 ms2. The design is based on the theoretical analysis using the Greens function formulism we developed earlier. The clean line shapes of the real and the imaginary parts of the Willis coefficient clear show, even by visual inspection, that the Kramers-Kronig relations are satisfied. Theoretical analysis agrees well with the major features of the experimental results.

physics.app-ph↗

arXiv2019

NAIRS: A Neural Attentive Interpretable Recommendation System

In this paper, we develop a neural attentive interpretable recommendation system, named NAIRS. A self-attention network, as a key component of the system, is designed to assign attention weights to interacted items of a user. This attention mechanism can distinguish the importance of the various interacted items in contributing to a user profile. Based on the user profiles obtained by the self-attention network, NAIRS offers personalized high-quality recommendation. Moreover, it develops visual cues to interpret recommendations. This demo application with the implementation of NAIRS enables users to interact with a recommendation system, and it persistently collects training data to improve the system. The demonstration and experimental results show the effectiveness of NAIRS.

cs.IR↗

arXiv2019

On optimal designs for non-regular models

Classically, Fisher information is the relevant object in defining optimal experimental designs. However, for models that lack certain regularity, the Fisher information does not exist and, hence, there is no notion of design optimality available in the literature. This article seeks to fill the gap by proposing a so-called Hellinger information, which generalizes Fisher information in the sense that the two measures agree in regular problems, but the former also exists for certain types of non-regular problems. We derive a Hellinger information inequality, showing that Hellinger information defines a lower bound on the local minimax risk of estimators. This provides a connection between features of the underlying model---in particular, the design---and the performance of estimators, motivating the use of this new Hellinger information for non-regular optimal design problems. Hellinger optimal designs are derived for several non-regular regression problems, with numerical results empirically demonstrating the efficiency of these designs compared to alternatives.

math.ST↗

arXiv2019

GCN-GAN: A Non-linear Temporal Link Prediction Model for Weighted Dynamic Networks

In this paper, we generally formulate the dynamics prediction problem of various network systems (e.g., the prediction of mobility, traffic and topology) as the temporal link prediction task. Different from conventional techniques of temporal link prediction that ignore the potential non-linear characteristics and the informative link weights in the dynamic network, we introduce a novel non-linear model GCN-GAN to tackle the challenging temporal link prediction task of weighted dynamic networks. The proposed model leverages the benefits of the graph convolutional network (GCN), long short-term memory (LSTM) as well as the generative adversarial network (GAN). Thus, the dynamics, topology structure and evolutionary patterns of weighted dynamic networks can be fully exploited to improve the temporal link prediction performance. Concretely, we first utilize GCN to explore the local topological characteristics of each single snapshot and then employ LSTM to characterize the evolving features of the dynamic networks. Moreover, GAN is used to enhance the ability of the model to generate the next weighted network snapshot, which can effectively tackle the sparsity and the wide-value-range problem of edge weights in real-life dynamic networks. To verify the model's effectiveness, we conduct extensive experiments on four datasets of different network systems and application scenarios. The experimental results demonstrate that our model achieves impressive results compared to the state-of-the-art competitors.

cs.SI↗

arXiv2018

Multi-Task Learning with Multi-View Attention for Answer Selection and Knowledge Base Question Answering

Answer selection and knowledge base question answering (KBQA) are two important tasks of question answering (QA) systems. Existing methods solve these two tasks separately, which requires large number of repetitive work and neglects the rich correlation information between tasks. In this paper, we tackle answer selection and KBQA tasks simultaneously via multi-task learning (MTL), motivated by the following motivations. First, both answer selection and KBQA can be regarded as a ranking problem, with one at text-level while the other at knowledge-level. Second, these two tasks can benefit each other: answer selection can incorporate the external knowledge from knowledge base (KB), while KBQA can be improved by learning contextual information from answer selection. To fulfill the goal of jointly learning these two tasks, we propose a novel multi-task learning scheme that utilizes multi-view attention learned from various perspectives to enable these tasks to interact with each other as well as learn more comprehensive sentence representations. The experiments conducted on several real-world datasets demonstrate the effectiveness of the proposed method, and the performance of answer selection and KBQA is improved. Also, the multi-view attention scheme is proved to be effective in assembling attentive information from different representational perspectives.

cs.CL↗

arXiv2018

Improving Automatic Source Code Summarization via Deep Reinforcement Learning

Code summarization provides a high level natural language description of the function performed by code, as it can benefit the software maintenance, code categorization and retrieval. To the best of our knowledge, most state-of-the-art approaches follow an encoder-decoder framework which encodes the code into a hidden space and then decode it into natural language space, suffering from two major drawbacks: a) Their encoders only consider the sequential content of code, ignoring the tree structure which is also critical for the task of code summarization, b) Their decoders are typically trained to predict the next word by maximizing the likelihood of next ground-truth word with previous ground-truth word given. However, it is expected to generate the entire sequence from scratch at test time. This discrepancy can cause an \textit{exposure bias} issue, making the learnt decoder suboptimal. In this paper, we incorporate an abstract syntax tree structure as well as sequential content of code snippets into a deep reinforcement learning framework (i.e., actor-critic network). The actor network provides the confidence of predicting the next word according to current state. On the other hand, the critic network evaluates the reward value of all possible extensions of the current state and can provide global guidance for explorations. We employ an advantage reward composed of BLEU metric to train both networks. Comprehensive experiments on a real-world dataset show the effectiveness of our proposed model when compared with some state-of-the-art methods.

cs.SE↗

arXiv2018

Dial2Desc: End-to-end Dialogue Description Generation

We first propose a new task named Dialogue Description (Dial2Desc). Unlike other existing dialogue summarization tasks such as meeting summarization, we do not maintain the natural flow of a conversation but describe an object or an action of what people are talking about. The Dial2Desc system takes a dialogue text as input, then outputs a concise description of the object or the action involved in this conversation. After reading this short description, one can quickly extract the main topic of a conversation and build a clear picture in his mind, without reading or listening to the whole conversation. Based on the existing dialogue dataset, we build a new dataset, which has more than one hundred thousand dialogue-description pairs. As a step forward, we demonstrate that one can get more accurate and descriptive results using a new neural attentive model that exploits the interaction between utterances from different speakers, compared with other baselines.

cs.CL↗

arXiv2018

Textually Guided Ranking Network for Attentional Image Retweet Modeling

Retweet prediction is a challenging problem in social media sites (SMS). In this paper, we study the problem of image retweet prediction in social media, which predicts the image sharing behavior that the user reposts the image tweets from their followees. Unlike previous studies, we learn user preference ranking model from their past retweeted image tweets in SMS. We first propose heterogeneous image retweet modeling network (IRM) that exploits users' past retweeted image tweets with associated contexts, their following relations in SMS and preference of their followees. We then develop a novel attentional multi-faceted ranking network learning framework with textually guided multi-modal neural networks for the proposed heterogenous IRM network to learn the joint image tweet representations and user preference representations for prediction task. The extensive experiments on a large-scale dataset from Twitter site shows that our method achieves better performance than other state-of-the-art solutions to the problem.

cs.IR↗

arXiv2018

The Coulomb interaction in monolayer transition-metal dichalcogenides

Recently, the celebrated Keldysh potential has been widely used to describe the Coulomb interaction of few-body complexes in monolayer transition-metal dichalcogenides. Using this potential to model charged excitons (trions), one finds a strong dependence of the binding energy on whether the monolayer is suspended in air, supported on SiO$_2$, or encapsulated in hexagonal boron-nitride. However, empirical values of the trion binding energies show weak dependence on the monolayer configuration. This deficiency indicates that the description of the Coulomb potential is still lacking in this important class of materials. We address this problem and derive a new potential form, which takes into account the three atomic sheets that compose a monolayer of transition-metal dichalcogenides. The new potential self-consistently supports (i) the non-hydrogenic Rydberg series of neutral excitons, and (ii) the weak dependence of the trion binding energy on the environment. Furthermore, we identify an important trion-lattice coupling due to the phonon cloud in the vicinity of charged complexes. Neutral excitons, on the other hand, have weaker coupling to the lattice due to the confluence of their charge neutrality and small Bohr radius.

cond-mat.mtrl-sci↗

arXiv2018

Investigating Capsule Networks with Dynamic Routing for Text Classification

In this study, we explore capsule networks with dynamic routing for text classification. We propose three strategies to stabilize the dynamic routing process to alleviate the disturbance of some noise capsules which may contain "background" information or have not been successfully trained. A series of experiments are conducted with capsule networks on six text classification benchmarks. Capsule networks achieve state of the art on 4 out of 6 datasets, which shows the effectiveness of capsule networks for text classification. We additionally show that capsule networks exhibit significant improvement when transfer single-label to multi-label text classification over strong baseline methods. To the best of our knowledge, this is the first work that capsule networks have been empirically investigated for text modeling.

cs.CL↗

arXiv2018

A Multi-sentiment-resource Enhanced Attention Network for Sentiment Classification

Deep learning approaches for sentiment classification do not fully exploit sentiment linguistic knowledge. In this paper, we propose a Multi-sentiment-resource Enhanced Attention Network (MEAN) to alleviate the problem by integrating three kinds of sentiment linguistic knowledge (e.g., sentiment lexicon, negation words, intensity words) into the deep neural network via attention mechanisms. By using various types of sentiment resources, MEAN utilizes sentiment-relevant information from different representation subspaces, which makes it more effective to capture the overall semantics of the sentiment, negation and intensity words for sentiment prediction. The experimental results demonstrate that MEAN has robust superiority over strong competitors.

cs.CL↗

arXiv2018

Leveraging Long and Short-term Information in Content-aware Movie Recommendation

Movie recommendation systems provide users with ranked lists of movies based on individual's preferences and constraints. Two types of models are commonly used to generate ranking results: long-term models and session-based models. While long-term models represent the interactions between users and movies that are supposed to change slowly across time, session-based models encode the information of users' interests and changing dynamics of movies' attributes in short terms. In this paper, we propose an LSIC model, leveraging Long and Short-term Information in Content-aware movie recommendation using adversarial training. In the adversarial process, we train a generator as an agent of reinforcement learning which recommends the next movie to a user sequentially. We also train a discriminator which attempts to distinguish the generated list of movies from the real records. The poster information of movies is integrated to further improve the performance of movie recommendation, which is specifically essential when few ratings are available. The experiments demonstrate that the proposed model has robust superiority over competitors and sets the state-of-the-art. We will release the source code of this work after publication.

cs.IR↗

arXiv2018

Virtual trions in the photoluminescence of monolayer transition-metal dichalcogenides

Photoluminescence experiments from monolayer transition-metal dichalcogenides often show that the binding energy of trions is conspicuously similar to the energy of optical phonons. This enigmatic coincidence calls into question whether phonons are involved in the radiative recombination process. We address this problem, unraveling an intriguing optical transition mechanism. Its initial state is a localized charge (electron or hole) and delocalized exciton. The final state is the localized charge, phonon and photon. In between, the intermediate state of the system is a virtual trion formed when the localized charge captures the exciton through emission of the phonon. We analyze the difference between radiative recombinations that involve real and virtual trions (i.e., with and without a phonon), providing useful ways to distinguish between the two in experiment.

cond-mat.mtrl-sci↗