Hang Li - NEC Corporation

Hang Li
Are you Hang Li?

Claim your profile, edit publications, add additional information:

Contact Details

Name
Hang Li
Affiliation
NEC Corporation
City
Minato-ku
Country
Japan

Pubs By Year

External Links

Pub Categories

 
Computer Science - Computation and Language (26)
 
Computer Science - Neural and Evolutionary Computing (13)
 
Computer Science - Learning (11)
 
Quantum Physics (8)
 
Computer Science - Artificial Intelligence (8)
 
Computer Science - Information Theory (6)
 
Mathematics - Information Theory (6)
 
Physics - Mesoscopic Systems and Quantum Hall Effect (4)
 
Computer Science - Information Retrieval (2)
 
Computer Science - Computer Vision and Pattern Recognition (2)
 
Physics - Plasma Physics (2)
 
Computer Science - Networking and Internet Architecture (1)
 
Physics - Superconductivity (1)
 
Cosmology and Nongalactic Astrophysics (1)
 
Physics - Optics (1)
 
Computer Science - Computational Complexity (1)
 
Mathematics - Probability (1)

Publications Authored By Hang Li

In typical neural machine translation~(NMT), the decoder generates a sentence word by word, packing all linguistic granularities in the same time-scale of RNN. In this paper, we propose a new type of decoder for NMT, which splits the decode state into two parts and updates them in two different time-scales. Specifically, we first predict a chunk time-scale state for phrasal modeling, on top of which multiple word time-scale states are generated. Read More

Quantum memory, capable of stopping flying photons and storing their quantum coherence, is essential for scalable quantum technologies. A broadband quantum memory operating at room temperature will enable building large-scale quantum systems for real-life applications, for instance, high-speed quantum repeater for long-distance quantum communication and synchronised multi-photon quantum sources for quantum computing and quantum simulation. Albeit advances of pushing bandwidth from narrowband to broadband and storage media from ultra-cold atomic gas to room-temperature atomic vapour, due to either intrinsic high noises or short lifetime, it is still challenging to find a room-temperature broadband quantum memory beyond conceptional demonstration. Read More

Nonadiabatic holonomic quantum computation has received increasing attention due to its robustness against control errors. However, all the previous schemes have to use at least two sequentially implemented gates to realize a general one-qubit gate. Based on two recent works, we construct two Hamiltonians and experimentally realized nonadiabatic holonomic gates by a single-shot implementation in a two-qubit nuclear magnetic resonance (NMR) system. Read More

The radiation symmetry and laser-plasma instabilities (LPIs) inside the conventional cylindrical hohlraum configuration are the two daunting challenges on the approach to ignition in indirectly driven inertial confinement fusion. Recently, near-vacuum cylindrical hohlraum (NVCH), octahedral spherical hohlraum (SH) and novel three-axis cylindrical hohlraum (TACH) were proposed to mitigate these issues. While the coupling efficiency might still be a critical risk. Read More

We design a heat engine with multi-heat-reservoir, ancillary system and quantum memory. We then derive an inequality related with the second law of thermodynamics, and give a new limitation about the work gain from the engine by analyzing the entropy change and quantum mutual information change during the process. In addition and remarkably, by considering two measurements and with the help of the entropic uncertainty relation with quantum memory, we find that the total work gains from the heat engine should be larger than a quantity related with quantum entanglement between the ancillary state and the quantum memory. Read More

Quantum computers promise to outperform their classical counterparts in many applications. Rapid experimental progress in the last two decades includes the first demonstrations of small-scale quantum processors, but realising large-scale quantum information processors capable of universal quantum control remains a challenge. One primary obstacle is the inadequacy of classical computers for the task of optimising the experimental control field as we scale up to large systems. Read More

We propose an online, end-to-end, neural generative conversational model for open-domain dialog. It is trained using a unique combination of offline two-phase supervised learning and online human-in-the-loop active learning. While most existing research proposes offline supervision or hand-crafted reward functions for online reinforcement, we devise a novel interactive learning mechanism based on a diversity-promoting heuristic for response generation and one-character user-feedback at each step. Read More

Building neural networks to query a knowledge base (a table) with natural language is an emerging research topic in NLP. The neural enquirer typically necessitates multiple steps of execution because of the compositionality of queries. In previous studies, researchers have developed either distributed enquirers or symbolic ones for table querying. Read More

Correlation functions are often employed to quantify the relationships among interdependent variables or sets of data. Recently, a new class of correlation functions, called Forrelation, has been introduced by Aaronson and Ambainis for studying the query complexity of quantum devices. It was found that there exists a quantum query algorithm solving 2-fold Forrelation problems with an exponential quantum speedup over all possible classical means, which represents essentially the largest possible separation between quantum and classical query complexities. Read More

Although end-to-end Neural Machine Translation (NMT) has achieved remarkable progress in the past two years, it suffers from a major drawback: translations generated by NMT systems often lack of adequacy. It has been widely observed that NMT tends to repeatedly translate some source words while mistakenly ignoring other words. To alleviate this problem, we propose a novel encoder-decoder-reconstructor framework for NMT. Read More

Conventional attention-based Neural Machine Translation (NMT) conducts dynamic alignment in generating the target sentence. By repeatedly reading the representation of source sentence, which keeps fixed after generated by the encoder (Bahdanau et al., 2015), the attention mechanism has greatly enhanced state-of-the-art NMT. Read More

Neural Machine Translation (NMT) is a new approach to machine translation that has made great progress in recent years. However, recent studies show that NMT generally produces fluent but inadequate translations (Tu et al. 2016b; Tu et al. Read More

The coupled dark energy model provides a possible approach to mitigate the coincidence problem of cosmological standard model. Here, the coupling term is assumed as $\bar{Q}=3H\xi_x\bar{\rho}_x$, which is related to the interaction rate and energy density of dark energy. We derive the background and perturbation evolution equations for several coupled models. Read More

In neural machine translation (NMT), generation of a target word depends on both source and target contexts. We find that source contexts have a direct impact on the adequacy of a translation while target contexts affect the fluency. Intuitively, generation of a content word should rely more on the source context and generation of a functional word should rely more on the target context. Read More

Energy harvesting communication has raised great research interests due to its wide applications and feasibility of commercialization. In this paper, we investigate the multiuser energy diversity. Specifically, we reveal the throughput gain coming from the increase of total available energy harvested over time/space and from the combined dynamics of batteries. Read More

In this paper, we propose phraseNet, a neural machine translator with a phrase memory which stores phrase pairs in symbolic form, mined from corpus or specified by human experts. For any given source sentence, phraseNet scans the phrase memory to determine the candidate phrase pairs and integrates tagging information in the representation of source sentence accordingly. The decoder utilizes a mixture of word-generating component and phrase-generating component, with a specifically designed strategy to generate a sequence of multiple words all at once. Read More

We propose to enhance the RNN decoder in a neural machine translator (NMT) with external memory, as a natural but powerful extension to the state in the decoding RNN. This memory-enhanced RNN decoder is called \textsc{MemDec}. At each time during decoding, \textsc{MemDec} will read from this memory and write to this memory once, both with content-based addressing. Read More

A novel ignition hohlraum for indirect-drive inertial confinement fusion is proposed, which is named as three-axis cylindrical hohlraum (TACH). TACH is a kind of 6 laser entrance holes (LEHs) hohlraum, which is made of three cylindrical hohlraums orthogonally jointed. Laser beams are injected through every entrance hole with the same incident angle of 55{\deg}. Read More

We study spin-orbit torques and charge pumping in magnetic quasi-one dimensional zigzag nanoribbons with hexagonal lattice, in the presence of large intrinsic spin-orbit coupling. Such a system experiences topological phase transition from a trivial band insulator to a quantum spin Hall insulator either by tuning the magnetization direction or the intrinsic spin-orbit coupling. We find that spin-charge conversion efficiency (i. Read More

The relevance between a query and a document in search can be represented as matching degree between the two objects. Latent space models have been proven to be effective for the task, which are often trained with click-through data. One technical challenge with the approach is that it is hard to train a model for tail queries and tail documents for which there are not enough clicks. Read More

Dropped Pronouns (DP) in which pronouns are frequently dropped in the source language but should be retained in the target language are challenge in machine translation. In response to this problem, we propose a semi-supervised approach to recall possibly missing pronouns in the translation. Firstly, we build training data for DP generation in which the DPs are automatically labelled according to the alignment information from a parallel corpus. Read More

We address an important problem in sequence-to-sequence (Seq2Seq) learning referred to as copying, in which certain segments in the input sequence are selectively replicated in the output sequence. A similar phenomenon is observable in human language communication. For example, humans tend to repeat entity names or even long phrases in conversation. Read More

Non-centrosymmetric superconductors, whose crystal structure is absent of inversion symmetry, have recently received special attentions due to the expectation of unconventional pairings and exotic physics associated with such pairings. The newly discovered superconductors A2Cr3As3 (A=K, Rb), featured by the quasi-one dimensional structure with conducting CrAs chains, belongs to such kind of superconductor. In this study, we are the first to report the finding that the superconductivity of A2Cr3As3 (A=K, Rb) has a positive correlation with the extent of non-centrosymmetry. Read More

Wireless sensor networks (WSNs) are effective for locating and tracking people and objects in various industrial environments. Since energy consumption is critical to prolonging the lifespan of WSNs, we propose an energy-efficient LOcalization and Tracking} (eLOT) system, using low-cost and portable hardware to enable highly accurate tracking of targets. Various fingerprint-based approaches for localization and tracking are implemented in eLOT. Read More

Attention mechanism has enhanced state-of-the-art Neural Machine Translation (NMT) by jointly learning to align and translate. It tends to ignore past alignment information, however, which often leads to over-translation and under-translation. To address this problem, we propose coverage-based NMT in this paper. Read More

This paper presents an end-to-end neural network model, named Neural Generative Question Answering (GENQA), that can generate answers to simple factoid questions, based on the facts in a knowledge-base. More specifically, the model is built on the encoder-decoder framework for sequence-to-sequence learning, while equipped with the ability to enquire the knowledge-base, and is trained on a corpus of question-answer pairs, with their associated triples in the knowledge-base. Empirical study shows the proposed model can effectively deal with the variations of questions and answers, and generate right and natural answers by referring to the facts in the knowledge-base. Read More

We proposed Neural Enquirer as a neural network architecture to execute a natural language (NL) query on a knowledge-base (KB) for answers. Basically, Neural Enquirer finds the distributed representation of a query and then executes it on knowledge-base tables to obtain the answer as one of the values in the tables. Unlike similar efforts in end-to-end training of semantic parsers, Neural Enquirer is fully "neuralized": it not only gives distributional representation of the query and the knowledge-base, but also realizes the execution of compositional queries as a series of differentiable operations, with intermediate results (consisting of annotations of the tables at different levels) saved on multiple layers of memory. Read More

We study spin-orbit torques in two dimensional hexagonal crystals such as graphene, silicene, germanene and stanene. The torque possesses two components, a field-like term due to inverse spin galvanic effect and an antidamping torque originating from Berry curvature in mixed spin-$k$ space. In the presence of staggered potential and exchange field, the valley degeneracy can be lifted and we obtain a valley-dependent Berry curvature, leading to a tunable antidamping torque by controlling the valley degree of freedom. Read More

We propose Neural Reasoner, a framework for neural network-based reasoning over natural language sentences. Given a question, Neural Reasoner can infer over multiple supporting facts and find an answer to the question in specific forms. Neural Reasoner has 1) a specific interaction-pooling mechanism, allowing it to examine multiple facts, and 2) a deep architecture, allowing it to model the complicated logical relations in reasoning tasks. Read More

Energy harvesting (EH) based communication has raised great research interests due to its wide application and the feasibility of commercialization. In this paper, we consider wireless communications with EH constraints at the transmitter. First, for delay-tolerant traffic, we investigate the long-term average throughput maximization problem and analytically compare the throughput performance against that of a system supported by conventional power supplies. Read More

We propose DEEPMEMORY, a novel deep architecture for sequence-to-sequence learning, which performs the task through a series of nonlinear transformations from the representation of the input sequence (e.g., a Chinese sentence) to the final output sequence (e. Read More

In this paper, we propose to employ the convolutional neural network (CNN) for the image question answering (QA). Our proposed CNN provides an end-to-end framework with convolutional architectures for learning not only the image and question representations, but also their inter-modal interactions to produce the answer. More specifically, our model consists of three CNNs: one image CNN to encode the image content, one sentence CNN to compose the words of the question, and one multimodal convolution layer to learn their joint representation for the classification in the space of candidate answer words. Read More

We propose a new MDS paradigm called reader-aware multi-document summarization (RA-MDS). Specifically, a set of reader comments associated with the news reports are also collected. The generated summaries from the reports for the event should be salient according to not only the reports but also the reader comments. Read More

In this paper, we propose multimodal convolutional neural networks (m-CNNs) for matching image and sentence. Our m-CNN provides an end-to-end framework with convolutional architectures to exploit image representation, word composition, and the matching relations between the two modalities. More specifically, it consists of one image CNN encoding the image content, and one matching CNN learning the joint representation of image and sentence. Read More

We propose a novel convolutional architecture, named $gen$CNN, for word sequence prediction. Different from previous work on neural network-based language modeling and generation (e.g. Read More

Semantic matching is of central importance to many natural language tasks \cite{bordes2014semantic,RetrievalQA}. A successful matching algorithm needs to adequately model the internal structures of language objects and the interaction between them. As a step toward this goal, we propose convolutional neural network models for matching two sentences, by adapting the convolutional strategy in vision and speech. Read More

We propose a novel method for translation selection in statistical machine translation, in which a convolutional neural network is employed to judge the similarity between a phrase pair in two languages. The specifically designed convolutional architecture encodes not only the semantic similarity of the translation pair, but also the context containing the phrase in the source language. Therefore, our approach is able to capture context-dependent semantic similarities of translation pairs. Read More

Many tasks in natural language processing, ranging from machine translation to question answering, can be reduced to the problem of matching two sentences or more generally two short texts. We propose a new approach to the problem, called Deep Match Tree (DeepMatch$_{tree}$), under a general setting. The approach consists of two components, 1) a mining algorithm to discover patterns for matching two short-texts, defined in the product space of dependency trees, and 2) a deep neural network for matching short texts using the mined patterns, as well as a learning algorithm to build the network having a sparse structure. Read More

We propose Neural Responding Machine (NRM), a neural network-based response generator for Short-Text Conversation. NRM takes the general encoder-decoder framework: it formalizes the generation of response as a decoding process based on the latent representation of the input text, while both encoding and decoding are realized with recurrent neural networks (RNN). The NRM is trained with a large amount of one-round conversation data collected from a microblogging service. Read More

The recently proposed neural network joint model (NNJM) (Devlin et al., 2014) augments the n-gram target language model with a heuristically chosen source context window, achieving state-of-the-art performance in SMT. In this paper, we give a more systematic treatment by summarizing the relevant source information through a convolutional architecture guided by the target information. Read More

This paper considers a heterogeneous ad hoc network with multiple transmitter-receiver pairs, in which all transmitters are capable of harvesting renewable energy from the environment and compete for one shared channel by random access. In particular, we focus on two different scenarios: the constant energy harvesting (EH) rate model where the EH rate remains constant within the time of interest and the i.i. Read More

Intraband and interband contributions to the current-driven spin-orbit torque in magnetic materials lacking inversion symmetry are theoretically studied using Kubo formula. In addition to the current-driven field-like torque ${\bf T}_{\rm FL}= \tau_{\rm FL}{\bf m}\times{\bf u}_{\rm so}$ (${\bf u}_{\rm so}$ being a unit vector determined by the symmetry of the spin-orbit coupling), we explore the intrinsic contribution arising from impurity-independent interband transitions and producing an anti-damping-like torque of the form ${\bf T}_{\rm DL}= \tau_{\rm DL}{\bf m}\times({\bf u}_{\rm so}\times{\bf m})$. Analytical expressions are obtained in the model case of a magnetic Rashba two-dimensional electron gas, while numerical calculations have been performed on a dilute magnetic semiconductor (Ga,Mn)As modeled by the Kohn-Luttinger Hamiltonian exchanged coupled to the Mn moments. Read More

We present a study of photo-excited magnetization dynamics in ferromagnetic (Ga,Mn)As films observed by time-resolved magneto-optical measurements. The magnetization precession triggered by linearly polarized optical pulses in the absence of an external field shows a strong dependence on photon frequency when the photo-excitation energy approaches the band-edge of (Ga,Mn)As. This can be understood in terms of magnetic anisotropy modulation by both laser heating of the sample and by hole-induced non-thermal paths. Read More

In recent years, wireless communication systems are expected to achieve more cost-efficient and sustainable operations by replacing conventional fixed power supplies such as batteries with energy harvesting (EH) devices, which could provide electric energy from renewable energy sources (e.g., solar and wind). Read More

The puzzling properties of quantum mechanics, wave-particle duality, entanglement and superposition, were dissected experimentally at past decades. However, hidden-variable (HV) models, based on three classical assumptions of wave-particle objectivity, determinism and independence, strive to explain or even defeat them. The development of quantum technologies enabled us to test experimentally the predictions of quantum mechanics and HV theories. Read More

Quantum gates in experiment are inherently prone to errors that need to be characterized before they can be corrected. Full characterization via quantum process tomography is impractical and often unnecessary. For most practical purposes, it is enough to estimate more general quantities such as the average fidelity. Read More

Many tasks in data mining and related fields can be formalized as matching between objects in two heterogeneous domains, including collaborative filtering, link prediction, image tagging, and web search. Machine learning techniques, referred to as learning-to-match in this paper, have been successfully applied to the problems. Among them, a class of state-of-the-art methods, named feature-based matrix factorization, formalize the task as an extension to matrix factorization by incorporating auxiliary features into the model. Read More

Identifying Hamiltonian of a quantum system is of vital importance for quantum information processing. In this Letter, we realized and benchmarked a quantum Hamiltonian identification algorithm recently proposed [Phys. Rev. Read More

Human computer conversation is regarded as one of the most difficult problems in artificial intelligence. In this paper, we address one of its key sub-problems, referred to as short text conversation, in which given a message from human, the computer returns a reasonable response to the message. We leverage the vast amount of short conversation data available on social media to study the issue. Read More