arXiv subjects

Bing Liu

Publications and source records attributed to Bing Liu.

At least 253 records · Page 14Linked to original sources

arXiv2018

Lattice Dynamics of Ultrathin FeSe Films on SrTiO3

Charge transfer and electron-phonon coupling (EPC) are proposed to be two important constituents associated with enhanced superconductivity in the single unit cell FeSe films on oxide surfaces. Using high-resolution electron energy loss spectroscopy combined with first-principles calculations, we have explored the lattice dynamics of ultrathin FeSe films grown on SrTiO3. We show that, despite the significant effect from the substrate on the electronic structure and superconductivity of the system, the FeSe phonons in the films are unaffected. The energy dispersion and linewidth associated with the Fe- and Se-derived vibrational modes are thickness- and temperature-independent. Theoretical calculations indicate the crucial role of antiferromagnetic correlation in FeSe to reproduce the experimental phonon dispersion. Importantly, the only detectable change due to the growth of FeSe films is the broadening of the Fuchs-Kliewer (F-K) phonons associated with the lattice vibrations of SrTiO$_3$(001) substrate. If EPC plays any role in the enhancement of film superconductivity, it must be the interfacial coupling between the electrons in FeSe film and the F-K phonons from substrate rather than the phonons of FeSe.

cond-mat.supr-con↗

arXiv2017

Context-aware Path Ranking for Knowledge Base Completion

Knowledge base (KB) completion aims to infer missing facts from existing ones in a KB. Among various approaches, path ranking (PR) algorithms have received increasing attention in recent years. PR algorithms enumerate paths between entity pairs in a KB and use those paths as features to train a model for missing fact prediction. Due to their good performances and high model interpretability, several methods have been proposed. However, most existing methods suffer from scalability (high RAM consumption) and feature explosion (trains on an exponentially large number of features) problems. This paper proposes a Context-aware Path Ranking (C-PR) algorithm to solve these problems by introducing a selective path exploration strategy. C-PR learns global semantics of entities in the KB using word embedding and leverages the knowledge of entity semantics to enumerate contextually relevant paths using bidirectional random walk. Experimental results on three large KBs show that the path features (fewer in number) discovered by C-PR not only improve predictive performance but also are more interpretable than existing baselines.

cs.CL↗

arXiv2017

A Study of Fermi-LAT GeV gamma-ray Emission towards the Magnetar-harboring Supernova Remnant Kesteven 73 and Its Molecular Environment

We report our independent GeV gamma-ray study of the young shell-type supernova remnant (SNR) Kes 73 which harbors a central magnetar, and CO-line millimeter observations toward the SNR. Using 7.6 years of Fermi-LAT observation data, we detected an extended gamma-ray source ("source A") with the centroid on the west of the SNR, with a significance of 21.6 sigma in 0.1-300 GeV and an error circle of 5.4 arcminute in angular radius. The gamma-ray spectrum cannot be reproduced by a pure leptonic emission or a pure emission from the magnetar, and thus a hadronic emission component is needed. The CO-line observations reveal a molecular cloud (MC) at V_LSR~90 km/s, which demonstrates morphological correspondence with the western boundary of the SNR brightened in multiwavelength. The 12CO (J=2-1)/12CO (J=1-0) ratio in the left (blue) wing 85-88 km/s is prominently elevated to ~1.1 along the northwestern boundary, providing kinematic evidence of the SNR-MC interaction. This SNR-MC association yields a kinematic distance 9 kpc to Kes 73. The MC is shown to be capable of accounting for the hadronic gamma-ray emission component. The gamma-ray spectrum can be interpreted with a pure hadronic emission or a magnetar+hadronic hybrid emission. In the case of pure hadronic emission, the spectral index of the protons is 2.4, very similar to that of the radio-emitting electrons, essentially consistent with the diffusive shock acceleration theory. In the case of magnetar+hadronic hybrid emission, a magnetic field decay rate >= 10^36 erg/s is needed to power the magnetar's curvature radiation.

astro-ph.HE↗

arXiv2017

End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning

In this paper, we present a neural network based task-oriented dialogue system that can be optimized end-to-end with deep reinforcement learning (RL). The system is able to track dialogue state, interface with knowledge bases, and incorporate query results into agent's responses to successfully complete task-oriented dialogues. Dialogue policy learning is conducted with a hybrid supervised and deep RL methods. We first train the dialogue agent in a supervised manner by learning directly from task-oriented dialogue corpora, and further optimize it with deep RL during its interaction with users. In the experiments on two different dialogue task domains, our model demonstrates robust performance in tracking dialogue state and producing reasonable system responses. We show that deep RL based optimization leads to significant improvement on task success rate and reduction in dialogue length comparing to supervised training model. We further show benefits of training task-oriented dialogue model end-to-end comparing to component-wise optimization with experiment results on dialogue simulations and human evaluations.

cs.CL↗

arXiv2017

Multi-Domain Adversarial Learning for Slot Filling in Spoken Language Understanding

The goal of this paper is to learn cross-domain representations for slot filling task in spoken language understanding (SLU). Most of the recently published SLU models are domain-specific ones that work on individual task domains. Annotating data for each individual task domain is both financially costly and non-scalable. In this work, we propose an adversarial training method in learning common features and representations that can be shared across multiple domains. Model that produces such shared representations can be combined with models trained on individual domain SLU data to reduce the amount of training samples required for developing a new domain. In our experiments using data sets from multiple domains, we show that adversarial training helps in learning better domain-general SLU models, leading to improved slot filling F1 scores. We further show that applying adversarial learning on domain-general model also helps in achieving higher slot filling performance when the model is jointly optimized with domain-specific models.

cs.CL↗

arXiv2017

Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models

Dialog response selection is an important step towards natural response generation in conversational agents. Existing work on neural conversational models mainly focuses on offline supervised learning using a large set of context-response pairs. In this paper, we focus on online learning of response selection in retrieval-based dialog systems. We propose a contextual multi-armed bandit model with a nonlinear reward function that uses distributed representation of text for online response selection. A bidirectional LSTM is used to produce the distributed representations of dialog context and responses, which serve as the input to a contextual bandit. In learning the bandit, we propose a customized Thompson sampling method that is applied to a polynomial feature space in approximating the reward. Experimental results on the Ubuntu Dialogue Corpus demonstrate significant performance gains of the proposed method over conventional linear contextual bandits. Moreover, we report encouraging response selection performance of the proposed neural bandit model using the Recall@k metric for a small set of online training samples.

cs.CL↗

arXiv2017

DOC: Deep Open Classification of Text Documents

Traditional supervised learning makes the closed-world assumption that the classes appeared in the test data must have appeared in training. This also applies to text learning or text classification. As learning is used increasingly in dynamic open environments where some new/test documents may not belong to any of the training classes, identifying these novel documents during classification presents an important problem. This problem is called open-world classification or open classification. This paper proposes a novel deep learning based approach. It outperforms existing state-of-the-art techniques dramatically.

cs.CL↗

arXiv2017

Iterative Policy Learning in End-to-End Trainable Task-Oriented Neural Dialog Models

In this paper, we present a deep reinforcement learning (RL) framework for iterative dialog policy optimization in end-to-end task-oriented dialog systems. Popular approaches in learning dialog policy with RL include letting a dialog agent to learn against a user simulator. Building a reliable user simulator, however, is not trivial, often as difficult as building a good dialog agent. We address this challenge by jointly optimizing the dialog agent and the user simulator with deep RL by simulating dialogs between the two agents. We first bootstrap a basic dialog agent and a basic user simulator by learning directly from dialog corpora with supervised training. We then improve them further by letting the two agents to conduct task-oriented dialogs and iteratively optimizing their policies with deep RL. Both the dialog agent and the user simulator are designed with neural network models that can be trained end-to-end. Our experiment results show that the proposed method leads to promising improvements on task success rate and total task reward comparing to supervised training and single-agent RL training baseline models.

cs.CL↗

arXiv2017

An End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialog

We present a novel end-to-end trainable neural network model for task-oriented dialog systems. The model is able to track dialog state, issue API calls to knowledge base (KB), and incorporate structured KB query results into system responses to successfully complete task-oriented dialogs. The proposed model produces well-structured system responses by jointly learning belief tracking and KB result processing conditioning on the dialog history. We evaluate the model in a restaurant search domain using a dataset that is converted from the second Dialog State Tracking Challenge (DSTC2) corpus. Experiment results show that the proposed model can robustly track dialog state given the dialog history. Moreover, our model demonstrates promising results in producing appropriate system responses, outperforming prior end-to-end trainable neural network models using per-response accuracy evaluation metrics.

cs.CL↗

arXiv2017

Large Magnetic Anisotropy of an Iron-Porphyrin Complex on Metal Substrate

Single magnetic atoms or molecules with large single-ion magnetic anisotropy are highly desired for future applications in high-density data storage and quantum computation. Here we have synthesized an Fe-porphyrin complex on Au(111) substrate in a controlled way, and revealed large magnetic anisotropy energy of more than 15 meV by low-temperature scanning tunneling microscopy and spectroscopy. Two magnetic states with opposite spin directions are discriminated by inelastic electron tunneling spectroscopy in varied magnetic field, and are found to have long spin lifetimes. First-principle calculations reveal that the weak ligand filed in this complex keeps the Fe atom in a high-spin state and preserves its large orbital angular momentum, which gives rise to an easy-axis perpendicular to the molecular plane and large magnetic anisotropy energy by spin-orbit coupling.

cond-mat.mes-hall↗

arXiv2017

Lifelong Learning CRF for Supervised Aspect Extraction

This paper makes a focused contribution to supervised aspect extraction. It shows that if the system has performed aspect extraction from many past domains and retained their results as knowledge, Conditional Random Fields (CRF) can leverage this knowledge in a lifelong learning manner to extract in a new domain markedly better than the traditional CRF without using this prior knowledge. The key innovation is that even after CRF training, the model can still improve its extraction with experiences in its applications.

cs.CL↗

arXiv2017

Learning Spatiotemporal-Aware Representation for POI Recommendation

The wide spread of location-based social networks brings about a huge volume of user check-in data, which facilitates the recommendation of points of interest (POIs). Recent advances on distributed representation shed light on learning low dimensional dense vectors to alleviate the data sparsity problem. Current studies on representation learning for POI recommendation embed both users and POIs in a common latent space, and users' preference is inferred based on the distance/similarity between a user and a POI. Such an approach is not in accordance with the semantics of users and POIs as they are inherently different objects. In this paper, we present a novel spatiotemporal aware (STA) representation, which models the spatial and temporal information as \emph{a relationship connecting users and POIs}. Our model generalizes the recent advances in knowledge graph embedding. The basic idea is that the embedding of a $<$time, location$>$ pair corresponds to a translation from embeddings of users to POIs. Since the POI embedding should be close to the user embedding plus the relationship vector, the recommendation can be performed by selecting the top-\emph{k} POIs similar to the translated POI, which are all of the same type of objects. We conduct extensive experiments on two real-world datasets. The results demonstrate that our STA model achieves the state-of-the-art performance in terms of high recommendation accuracy, robustness to data sparsity and effectiveness in handling cold start problem.

cs.IR↗

arXiv2017

Superconducting transition of FeSe/SrTiO3 induced by adsorption of semiconducting organic molecules

We prepared superconducting and non-superconducting FeSe films on SrTiO3(001) substrates (FeSe/STO) and investigated the superconducting transition induced by charge transfer between organic molecules and FeSe layers by low temperature scanning tunneling microscopy and spectroscopy. At low coverage, donor- and acceptor-type molecules adsorbed preferentially on the non-superconducting and superconducting FeSe layers, respectively. Superconductivity was induced by donor molecules on non-superconducting FeSe layer, while the superconductivity was suppressed near acceptor molecules. The corresponding evolutions of electronic states and work function were also resolved by scanning tunneling microscopy. These results illustrate the important role played by local electron concentration in the superconducting transition of FeSe/STO.

cond-mat.supr-con↗

arXiv2017

Epitaxial Growth and Band Structure of Te Film on Graphene

Tellurium (Te) films with monolayer and few-layer thickness are obtained by molecular beam epitaxy on a graphene/6H-SiC(0001) substrate and investigated by in situ scanning tunneling microscopy and spectroscopy (STM/STS). We reveal that the Te films are composed of parallel-arranged helical Te chains flat-lying on the graphene surface, exposing the (1x1) facet of (10-10) of the bulk crystal. The band gap of Te films increases monotonically with decreasing thickness, reaching ~0.92 eV for the monolayer Te. An explicit band bending at the edge between the monolayer Te and graphene substrate is visualized. With the thickness controlled in atomic scale, Te films show potential applications of in electronics and optoelectronics.

cond-mat.mtrl-sci↗

arXiv2017

Dialog Context Language Modeling with Recurrent Neural Networks

In this work, we propose contextual language models that incorporate dialog level discourse information into language modeling. Previous works on contextual language model treat preceding utterances as a sequence of inputs, without considering dialog interactions. We design recurrent neural network (RNN) based contextual language models that specially track the interactions between speakers in a dialog. Experiment results on Switchboard Dialog Act Corpus show that the proposed model outperforms conventional single turn based RNN language model by 3.3% on perplexity. The proposed models also demonstrate advantageous performance over other competitive contextual language models.

cs.CL↗

arXiv2016

Supervised Opinion Aspect Extraction by Exploiting Past Extraction Results

One of the key tasks of sentiment analysis of product reviews is to extract product aspects or features that users have expressed opinions on. In this work, we focus on using supervised sequence labeling as the base approach to performing the task. Although several extraction methods using sequence labeling methods such as Conditional Random Fields (CRF) and Hidden Markov Models (HMM) have been proposed, we show that this supervised approach can be significantly improved by exploiting the idea of concept sharing across multiple domains. For example, "screen" is an aspect in iPhone, but not only iPhone has a screen, many electronic devices have screens too. When "screen" appears in a review of a new domain (or product), it is likely to be an aspect too. Knowing this information enables us to do much better extraction in the new domain. This paper proposes a novel extraction method exploiting this idea in the context of supervised sequence labeling. Experimental results show that it produces markedly better results than without using the past information.

cs.CL↗

arXiv2016

Modeling Review Spam Using Temporal Patterns and Co-bursting Behaviors

Online reviews play a crucial role in helping consumers evaluate and compare products and services. However, review hosting sites are often targeted by opinion spamming. In recent years, many such sites have put a great deal of effort in building effective review filtering systems to detect fake reviews and to block malicious accounts. Thus, fraudsters or spammers now turn to compromise, purchase or even raise reputable accounts to write fake reviews. Based on the analysis of a real-life dataset from a review hosting site (dianping.com), we discovered that reviewers' posting rates are bimodal and the transitions between different states can be utilized to differentiate spammers from genuine reviewers. Inspired by these findings, we propose a two-mode Labeled Hidden Markov Model to detect spammers. Experimental results show that our model significantly outperforms supervised learning using linguistic and behavioral features in identifying spammers. Furthermore, we found that when a product has a burst of reviews, many spammers are likely to be actively involved in writing reviews to the product as well as to many other products. We then propose a novel co-bursting network for detecting spammer groups. The co-bursting network enables us to produce more accurate spammer groups than the current state-of-the-art reviewer-product (co-reviewing) network.

cs.SI↗

arXiv2016

Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling

Attention-based encoder-decoder neural network models have recently shown promising results in machine translation and speech recognition. In this work, we propose an attention-based neural network model for joint intent detection and slot filling, both of which are critical steps for many speech understanding and dialog systems. Unlike in machine translation and speech recognition, alignment is explicit in slot filling. We explore different strategies in incorporating this alignment information to the encoder-decoder framework. Learning from the attention mechanism in encoder-decoder model, we further propose introducing attention to the alignment-based RNN models. Such attentions provide additional information to the intent classification and slot label prediction. Our independent task models achieve state-of-the-art intent detection error rate and slot filling F1 score on the benchmark ATIS task. Our joint training model further obtains 0.56% absolute (23.8% relative) error reduction on intent detection and 0.23% absolute gain on slot filling over the independent task models.

cs.CL↗