arXiv subjects

Ming Zhang

Publications and source records attributed to Ming Zhang.

At least 415 records · Page 23Linked to original sources

arXiv2017

Syntax Aware LSTM Model for Chinese Semantic Role Labeling

As for semantic role labeling (SRL) task, when it comes to utilizing parsing information, both traditional methods and recent recurrent neural network (RNN) based methods use the feature engineering way. In this paper, we propose Syntax Aware Long Short Time Memory(SA-LSTM). The structure of SA-LSTM modifies according to dependency parsing information in order to model parsing information directly in an architecture engineering way instead of feature engineering way. We experimentally demonstrate that SA-LSTM gains more improvement from the model architecture. Furthermore, SA-LSTM outperforms the state-of-the-art on CPB 1.0 significantly according to Student t-test ($p<0.05$).

cs.CL↗

arXiv2017

Two-Bit Networks for Deep Learning on Resource-Constrained Embedded Devices

With the rapid proliferation of Internet of Things and intelligent edge devices, there is an increasing need for implementing machine learning algorithms, including deep learning, on resource-constrained mobile embedded devices with limited memory and computation power. Typical large Convolutional Neural Networks (CNNs) need large amounts of memory and computational power, and cannot be deployed on embedded devices efficiently. We present Two-Bit Networks (TBNs) for model compression of CNNs with edge weights constrained to (-2, -1, 1, 2), which can be encoded with two bits. Our approach can reduce the memory usage and improve computational efficiency significantly while achieving good performance in terms of classification accuracy, thus representing a reasonable tradeoff between model size and performance.

cs.LG↗

arXiv2016

Less is More: Learning Prominent and Diverse Topics for Data Summarization

Statistical topic models efficiently facilitate the exploration of large-scale data sets. Many models have been developed and broadly used to summarize the semantic structure in news, science, social media, and digital humanities. However, a common and practical objective in data exploration tasks is not to enumerate all existing topics, but to quickly extract representative ones that broadly cover the content of the corpus, i.e., a few topics that serve as a good summary of the data. Most existing topic models fit exactly the same number of topics as a user specifies, which have imposed an unnecessary burden to the users who have limited prior knowledge. We instead propose new models that are able to learn fewer but more representative topics for the purpose of data summarization. We propose a reinforced random walk that allows prominent topics to absorb tokens from similar and smaller topics, thus enhances the diversity among the top topics extracted. With this reinforced random walk as a general process embedded in classical topic models, we obtain \textit{diverse topic models} that are able to extract the most prominent and diverse topics from data. The inference procedures of these diverse topic models remain as simple and efficient as the classical models. Experimental results demonstrate that the diverse topic models not only discover topics that better summarize the data, but also require minimal prior knowledge of the users.

cs.LG↗

arXiv2016

Context-aware Natural Language Generation with Recurrent Neural Networks

This paper studied generating natural languages at particular contexts or situations. We proposed two novel approaches which encode the contexts into a continuous semantic representation and then decode the semantic representation into text sequences with recurrent neural networks. During decoding, the context information are attended through a gating mechanism, addressing the problem of long-range dependency caused by lengthy sequences. We evaluate the effectiveness of the proposed approaches on user review data, in which rich contexts are available and two informative contexts, sentiments and products, are selected for evaluation. Experiments show that the fake reviews generated by our approaches are very natural. Results of fake review detection with human judges show that more than 50\% of the fake reviews are misclassified as the real reviews, and more than 90\% are misclassified by existing state-of-the-art fake review detection algorithm.

cs.CL↗

arXiv2016

Improving Color Constancy by Discounting the Variation of Camera Spectral Sensitivity

It is an ill-posed problem to recover the true scene colors from a color biased image by discounting the effects of scene illuminant and camera spectral sensitivity (CSS) at the same time. Most color constancy (CC) models have been designed to first estimate the illuminant color, which is then removed from the color biased image to obtain an image taken under white light, without the explicit consideration of CSS effect on CC. This paper first studies the CSS effect on illuminant estimation arising in the inter-dataset-based CC (inter-CC), i.e., training a CC model on one dataset and then testing on another dataset captured by a distinct CSS. We show the clear degradation of existing CC models for inter-CC application. Then a simple way is proposed to overcome such degradation by first learning quickly a transform matrix between the two distinct CSSs (CSS-1 and CSS-2). The learned matrix is then used to convert the data (including the illuminant ground truth and the color biased images) rendered under CSS-1 into CSS-2, and then train and apply the CC model on the color biased images under CSS-2, without the need of burdensome acquiring of training set under CSS-2. Extensive experiments on synthetic and real images show that our method can clearly improve the inter-CC performance for traditional CC algorithms. We suggest that by taking the CSS effect into account, it is more likely to obtain the truly color constant images invariant to the changes of both illuminant and camera sensors.

cs.CV↗

arXiv2016

Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems

Open-domain human-computer conversation has attracted much attention in the field of NLP. Contrary to rule- or template-based domain-specific dialog systems, open-domain conversation usually requires data-driven approaches, which can be roughly divided into two categories: retrieval-based and generation-based systems. Retrieval systems search a user-issued utterance (called a query) in a large database, and return a reply that best matches the query. Generative approaches, typically based on recurrent neural networks (RNNs), can synthesize new replies, but they suffer from the problem of generating short, meaningless utterances. In this paper, we propose a novel ensemble of retrieval-based and generation-based dialog systems in the open domain. In our approach, the retrieved candidate, in addition to the original query, is fed to an RNN-based reply generator, so that the neural model is aware of more information. The generated reply is then fed back as a new candidate for post-reranking. Experimental results show that such ensemble outperforms each single part of it by a large margin.

cs.CL↗

arXiv2016

Dialogue Session Segmentation by Embedding-Enhanced TextTiling

In human-computer conversation systems, the context of a user-issued utterance is particularly important because it provides useful background information of the conversation. However, it is unwise to track all previous utterances in the current session as not all of them are equally important. In this paper, we address the problem of session segmentation. We propose an embedding-enhanced TextTiling approach, inspired by the observation that conversation utterances are highly noisy, and that word embeddings provide a robust way of capturing semantics. Experimental results show that our approach achieves better performance than the TextTiling, MMD approaches.

cs.CL↗

arXiv2016

Coexistent physics of massive black holes in the phase transitions

The coexistent physics of de Rham-Gabada-dze-Tolley (dRGT) massive black holes and holographic massive black holes is investigated in the extended phase space where the cosmological constant is viewed as pressure. Van der Waals like phase transitions are found for both of them. Coexistent curves of reduced pressure and reduced temperature are found to be different from that of RN-AdS black holes. Coexistent curves of reduced Gibbs free energy and reduced pressure show that Gibbs free energy in the canonical ensemble decreases monotonically with the increasing pressure. The concept number density is introduced to study the coexistent physics. It is uncovered that with the increasing pressure, the number densities of small black holes (SBHs) and large black holes (LBHs) change monotonically in the contrary directions till finally reaching the same value at the critical points of the phase transitions. In other words, with the increasing pressure the number density differences between SBHs and LBHs decrease monotonically before disappearance at the critical points. Further more, HEPM thermodynamic scalar curvature differences between SBHs and LBHs are found to decrease monotonically to zero when approaching to the critical points, which is similar as a RN-AdS black hole. We propose that both the number density difference and the HEPM scalar curvature difference can be order parameters describing the SBH/LBH phase transition and judging the upcoming of critical point where a second-order phase transition takes place. These results provide us with new recognition of the massive gravity. The thermodynamics in the extended phase space of AdS black holes is enriched.

gr-qc↗

arXiv2016

World Knowledge as Indirect Supervision for Document Clustering

One of the key obstacles in making learning protocols realistic in applications is the need to supervise them, a costly process that often requires hiring domain experts. We consider the framework to use the world knowledge as indirect supervision. World knowledge is general-purpose knowledge, which is not designed for any specific domain. Then the key challenges are how to adapt the world knowledge to domains and how to represent it for learning. In this paper, we provide an example of using world knowledge for domain dependent document clustering. We provide three ways to specify the world knowledge to domains by resolving the ambiguity of the entities and their types, and represent the data with world knowledge as a heterogeneous information network. Then we propose a clustering algorithm that can cluster multiple types and incorporate the sub-type information as constraints. In the experiments, we use two existing knowledge bases as our sources of world knowledge. One is Freebase, which is collaboratively collected knowledge about entities and their organizations. The other is YAGO2, a knowledge base automatically extracted from Wikipedia and maps knowledge to the linguistic knowledge base, WordNet. Experimental results on two text benchmark datasets (20newsgroups and RCV1) show that incorporating world knowledge as indirect supervision can significantly outperform the state-of-the-art clustering algorithms as well as clustering algorithms enhanced with world knowledge features.

cs.LG↗

arXiv2016

On-chip coherent conversion of photonic quantum signals between different degrees of freedom

In the quantum world, a single particle can have various degrees of freedom to encode quantum information. Controlling multiple degrees of freedom simultaneously is necessary to describe a particle fully and, therefore, to use it more efficiently. Here we introduce the transverse waveguide-mode degree of freedom to quantum photonic integrated circuits, and demonstrate the coherent conversion of a photonic quantum state between path, polarization and transverse waveguide-mode degrees of freedom on a single chip. The preservation of quantum coherence in these conversion processes is proven by single-photon and two-photon quantum interference using a fibre beam splitter or on-chip beam splitters. These results provide us with the ability to control and convert multiple degrees of freedom of photons for quantum photonic integrated circuit-based quantum information process.

quant-ph↗

arXiv2016

Unsupervised Word and Dependency Path Embeddings for Aspect Term Extraction

In this paper, we develop a novel approach to aspect term extraction based on unsupervised learning of distributed representations of words and dependency paths. The basic idea is to connect two words (w1 and w2) with the dependency path (r) between them in the embedding space. Specifically, our method optimizes the objective w1 + r = w2 in the low-dimensional space, where the multi-hop dependency paths are treated as a sequence of grammatical relations and modeled by a recurrent neural network. Then, we design the embedding features that consider linear context and dependency context information, for the conditional random field (CRF) based aspect term extraction. Experimental results on the SemEval datasets show that, (1) with only embedding features, we can achieve state-of-the-art results; (2) our embedding method which incorporates the syntactic information among words yields better performance than other representative ones in aspect term extraction.

cs.CL↗

arXiv2016

StalemateBreaker: A Proactive Content-Introducing Approach to Automatic Human-Computer Conversation

Existing open-domain human-computer conversation systems are typically passive: they either synthesize or retrieve a reply provided a human-issued utterance. It is generally presumed that humans should take the role to lead the conversation and introduce new content when a stalemate occurs, and that the computer only needs to "respond." In this paper, we propose StalemateBreaker, a conversation system that can proactively introduce new content when appropriate. We design a pipeline to determine when, what, and how to introduce new content during human-computer conversation. We further propose a novel reranking algorithm Bi-PageRank-HITS to enable rich interaction between conversation context and candidate replies. Experiments show that both the content-introducing approach and the reranking algorithm are effective. Our full StalemateBreaker model outperforms a state-of-the-practice conversation system by +14.4% p@1 when a stalemate occurs.

cs.CL↗

arXiv2016

Visualizing Large-scale and High-dimensional Data

We study the problem of visualizing large-scale and high-dimensional data in a low-dimensional (typically 2D or 3D) space. Much success has been reported recently by techniques that first compute a similarity structure of the data points and then project them into a low-dimensional space with the structure preserved. These two steps suffer from considerable computational costs, preventing the state-of-the-art methods such as the t-SNE from scaling to large-scale and high-dimensional data (e.g., millions of data points and hundreds of dimensions). We propose the LargeVis, a technique that first constructs an accurately approximated K-nearest neighbor graph from the data and then layouts the graph in the low-dimensional space. Comparing to t-SNE, LargeVis significantly reduces the computational cost of the graph construction step and employs a principled probabilistic model for the visualization step, the objective of which can be effectively optimized through asynchronous stochastic gradient descent with a linear time complexity. The whole procedure thus easily scales to millions of high-dimensional data points. Experimental results on real-world data sets demonstrate that the LargeVis outperforms the state-of-the-art methods in both efficiency and effectiveness. The hyper-parameters of LargeVis are also much more stable over different data sets.

cs.LG↗

arXiv2015

The East-Asian VLBI Network

The East-Asian VLBI Network (EAVN) is the international VLBI facility in East Asia and is conducted in collaboration with China, Japan, and Korea. The EAVN consists of VLBI arrays operated in each East Asian country, containing 21 radio telescopes and three correlators. The EAVN will be mainly operated at 6.7 (C-band), 8 (X-band), 22 (K-band), and 43 GHz (Q-band), although the EAVN has an ability to conduct observations at 1.6 - 129 GHz. We have conducted fringe test observations eight times to date at 8 and 22 GHz and fringes have been successfully detected at both frequencies. We have also conducted science commissioning observations of 6.7 GHz methanol masers in massive star-forming regions. The EAVN will be operational from the second half of 2017, providing complementary results with the FAST on AGNs, massive star-forming regions, and evolved stars with high angular resolution at cm- to mm-wavelengths.

astro-ph.IM↗

arXiv2015

High performance FeSe0.5Te0.5 thin films grown at low temperature by pulsed laser deposition

We report on fully epitaxial FeSe0.5Te0.5 (FST) thin films with high-quality grown on CaF2 (00l) substrate at a low temperature of 300°C by pulsed laser deposition. The transport Jc of thin films is up to 1.36 MA/cm2 in self-field and 0.97 MA/cm2 in 9 T at 4.2 K, indicating very weak field dependence. A nearly isotropy of Jc (γ= Jc(H//ab)/Jc(H//c) as low as 1.09 at 9 T is achieved in the FST thin films. Moreover, no clear amorphous interfacial layer presents between the film and the substrate probably ascribing to low temperature and low laser repetition rate grown, while the thickness of reaction layer is approximate 5 nm in many other works. The evidences of transmission electron microscopy show some lattices with lateral size of < 5 nm x 20 nm seem to be disturbed. Those location defects are thought to be responsible for nearly isotropic behavior of superconductivity.

cond-mat.supr-con↗

arXiv2015

LINE: Large-scale Information Network Embedding

This paper studies the problem of embedding very large information networks into low-dimensional vector spaces, which is useful in many tasks such as visualization, node classification, and link prediction. Most existing graph embedding methods do not scale for real world information networks which usually contain millions of nodes. In this paper, we propose a novel network embedding method called the "LINE," which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted. The method optimizes a carefully designed objective function that preserves both the local and global network structures. An edge-sampling algorithm is proposed that addresses the limitation of the classical stochastic gradient descent and improves both the effectiveness and the efficiency of the inference. Empirical experiments prove the effectiveness of the LINE on a variety of real-world information networks, including language networks, social networks, and citation networks. The algorithm is very efficient, which is able to learn the embedding of a network with millions of vertices and billions of edges in a few hours on a typical single machine. The source code of the LINE is available online.

cs.LG↗

arXiv2014

Critical behaviors of black holes in the Einstein-Maxwell gravity with conformal anomaly

We study $P-V$ critical behavior of 4-dimensional AdS black hole in the Einstein-Maxwell gravity with conformal anomaly by treating the cosmological constant as a variable related to the thermodynamic pressure. It shows that there is no phase transition if taking $k=0$ or -1. When the charge $q_1$ of conformal field and the coefficient $α$ satisfy a certain relation, the Van der Waal like phase transition for the spherical black hole can occur in case of the temperature is lower than the small critical temperature or higher than the large one. We also evaluate the critical exponents of the phase transitions and find that the thermodynamic exponents associated with this 4-dimensional AdS black hole coincide with those of the van der Waals fluid.

hep-th↗

arXiv2014

$P-V$ criticality of AdS black hole in the Einstein-Maxwell-power-Yang-Mills gravity

We study the $P-V$ critical behaivor of N-dimensional AdS black holes in Einstein-Maxwell-power-Yang-Mills gravity. Our results show the existence of the Van der Waals like small-large black hole phase transitions when taking some special values of charges of the Maxwell and Yang-Mills (YM) fields. Further to calculate the critical exponents of the black holes at the critical point, we find that they are the same as those in the Van der Waals liquid-gas system.

hep-th↗