arXiv subjects

Bing Liu

Publications and source records attributed to Bing Liu.

At least 217 records · Page 12Linked to original sources

arXiv2020

A Deep Learning Framework for Hydrogen-fueled Turbulent Combustion Simulation

The high cost of high-resolution computational fluid/flame dynamics (CFD) has hindered its application in combustion related design, research and optimization. In this study, we propose a new framework for turbulent combustion simulation based on the deep learning approach. An optimized deep convolutional neural network (CNN) inspired from a U-Net architecture and inception module is designed for constructing the framework of the deep learning solver, named CFDNN. CFDNN is then trained on the simulation results of hydrogen combustion in a cavity with different inlet velocities. After training, CFDNN can not only accurately predict the flow and combustion fields within the range of the training set, but also shows an extrapolation ability for prediction outside the training set. The results from CFDNN solver show excellent consistency with the conventional CFD results in terms of both predicted spatial distributions and temporal dynamics. Meanwhile, two orders of magnitude of acceleration is achieved by using CFDNN solver compared to the conventional CFD solver. The successful development of such a deep learning-based solver opens up new possibilities of low-cost, high-accuracy simulations, fast prototyping, design optimization and real-time control of combustion systems such as gas turbines and scramjets.

physics.flu-dyn↗

arXiv2019

Lifelong and Interactive Learning of Factual Knowledge in Dialogues

Dialogue systems are increasingly using knowledge bases (KBs) storing real-world facts to help generate quality responses. However, as the KBs are inherently incomplete and remain fixed during conversation, it limits dialogue systems' ability to answer questions and to handle questions involving entities or relations that are not in the KB. In this paper, we make an attempt to propose an engine for Continuous and Interactive Learning of Knowledge (CILK) for dialogue systems to give them the ability to continuously and interactively learn and infer new knowledge during conversations. With more knowledge accumulated over time, they will be able to learn better and answer more questions. Our empirical evaluation shows that CILK is promising.

cs.CL↗

arXiv2019

Transformation of Dense and Sparse Text Representations

Sparsity is regarded as a desirable property of representations, especially in terms of explanation. However, its usage has been limited due to the gap with dense representations. Most NLP research progresses in recent years are based on dense representations. Thus the desirable property of sparsity cannot be leveraged. Inspired by Fourier Transformation, in this paper, we propose a novel Semantic Transformation method to bridge the dense and sparse spaces, which can facilitate the NLP research to shift from dense space to sparse space or to jointly use both spaces. The key idea of the proposed approach is to use a Forward Transformation to transform dense representations to sparse representations. Then some useful operations in the sparse space can be performed over the sparse representations, and the sparse representations can be used directly to perform downstream tasks such as text classification and natural language inference. Then, a Backward Transformation can also be carried out to transform those processed sparse representations to dense representations. Experiments using classification tasks and natural language inference task show that the proposed Semantic Transformation is effective.

cs.CL↗

arXiv2019

Review Conversational Reading Comprehension

Inspired by conversational reading comprehension (CRC), this paper studies a novel task of leveraging reviews as a source to build an agent that can answer multi-turn questions from potential consumers of online businesses. We first build a review CRC dataset and then propose a novel task-aware pre-tuning step running between language model (e.g., BERT) pre-training and domain-specific fine-tuning. The proposed pre-tuning requires no data annotation, but can greatly enhance the performance on our end task. Experimental results show that the proposed approach is highly effective and has competitive performance as the supervised approach. The dataset is available at \url{https://github.com/howardhsu/RCRC}

cs.CL↗

arXiv2019

A Failure of Aspect Sentiment Classifiers and an Adaptive Re-weighting Solution

Aspect-based sentiment classification (ASC) is an important task in fine-grained sentiment analysis.~Deep supervised ASC approaches typically model this task as a pair-wise classification task that takes an aspect and a sentence containing the aspect and outputs the polarity of the aspect in that sentence. However, we discovered that many existing approaches fail to learn an effective ASC classifier but more like a sentence-level sentiment classifier because they have difficulty to handle sentences with different polarities for different aspects.~This paper first demonstrates this problem using several state-of-the-art ASC models. It then proposes a novel and general adaptive re-weighting (ARW) scheme to adjust the training to dramatically improve ASC for such complex sentences. Experimental results show that the proposed framework is effective \footnote{The dataset and code are available at \url{https://github.com/howardhsu/ASC_failure}.}.

cs.CL↗

arXiv2019

Learning with Noisy Labels for Sentence-level Sentiment Classification

Deep neural networks (DNNs) can fit (or even over-fit) the training data very well. If a DNN model is trained using data with noisy labels and tested on data with clean labels, the model may perform poorly. This paper studies the problem of learning with noisy labels for sentence-level sentiment classification. We propose a novel DNN model called NetAb (as shorthand for convolutional neural Networks with Ab-networks) to handle noisy labels during training. NetAb consists of two convolutional neural networks, one with a noise transition layer for dealing with the input noisy labels and the other for predicting 'clean' labels. We train the two networks using their respective loss functions in a mutual reinforcement manner. Experimental results demonstrate the effectiveness of the proposed model.

cs.CL↗

arXiv2019

Modeling Multi-Action Policy for Task-Oriented Dialogues

Dialogue management (DM) plays a key role in the quality of the interaction with the user in a task-oriented dialogue system. In most existing approaches, the agent predicts only one DM policy action per turn. This significantly limits the expressive power of the conversational agent and introduces unwanted turns of interactions that may challenge users' patience. Longer conversations also lead to more errors and the system needs to be more robust to handle them. In this paper, we compare the performance of several models on the task of predicting multiple acts for each turn. A novel policy model is proposed based on a recurrent cell called gated Continue-Act-Slots (gCAS) that overcomes the limitations of the existing models. Experimental results show that gCAS outperforms other approaches. The code is available at https://leishu02.github.io/

cs.CL↗

arXiv2019

Superconductivity of the FeSe/SrTiO3 Interface in the View of BCS-BEC Crossover

In paired Fermi systems, strong many-body effects exhibit in the crossover regime between the Bardeen-Cooper-Schrieffer (BCS) and the Bose-Einstein condensation (BEC) limits. The concept of the BCS-BEC crossover, which is studied intensively in the research field of cold atoms, has been extended to condensed matters. Here, by analyzing the typical superconductors within the BCS-BEC phase diagram, we find that FeSe-based superconductors are prone to shift their positions in the BCS-BEC crossover regime by charge doping or substrate substitution, since their Fermi energies and the superconducting gap sizes are comparable. Especially at the interface of a single-layer FeSe on SrTiO3 substrate, the superconductivity is relocated closer to the crossover unitary than other doped FeSe-based materials, indicating that the pairing interaction is effectively modulated. We further show that hole-doping can drive the interfacial system into the phase with possible pre-paired electrons, demonstrating its flexible tunability within the BCS-BEC crossover regime.

cond-mat.supr-con↗

arXiv2019

The GeV emission in the field of the star-forming region W30 revisited

We present a detailed study of the gamma-ray emission from the direction of the star-forming region W30 based on a decade of the Fermi Large Area Telescope data in the 0.3-300 GeV photon energy range. The morphological and spectral analyses allow us to resolve the gamma-ray emission into two extended structures from different origins. One of them mostly overlaps with the supernova remnant (SNR) G8.7-0.1 and has a soft spectrum that resembles with the spectra of other middle-aged SNRs interacting with molecular clouds. The other shows remarkable spatial and spectral consistency with the TeV emission from HESS J1804-216, and its spectrum could be naturally explained by inverse Compton scattering of electrons like a number of TeV gamma-ray emitting pulsar wind nebulae. Thus we attribute this source to the nebula around the pulsar PSR J1803-2137.

astro-ph.HE↗

arXiv2019

Flexibly-Structured Model for Task-Oriented Dialogues

This paper proposes a novel end-to-end architecture for task-oriented dialogue systems. It is based on a simple and practical yet very effective sequence-to-sequence approach, where language understanding and state tracking tasks are modeled jointly with a structured copy-augmented sequential decoder and a multi-label decoder for each slot. The policy engine and language generation tasks are modeled jointly following that. The copy-augmented sequential decoder deals with new or unknown values in the conversation, while the multi-label decoder combined with the sequential decoder ensures the explicit assignment of values to slots. On the generation part, slot binary classifiers are used to improve performance. This architecture is scalable to real-world scenarios and is shown through an empirical evaluation to achieve state-of-the-art performance on both the Cambridge Restaurant dataset and the Stanford in-car assistant dataset\footnote{The code is available at \url{https://github.com/uber-research/FSDM}}

cs.CL↗

arXiv2019

Real-Space Investigation of the Charge Density Wave in VTe2 Monolayer with Rotational and Mirror Symmetries Broken

Recently the charge density wave (CDW) in vanadium dichalcogenides have attracted increasing research interests, but a real-space investigation on the symmetry breaking of the CDW state in VTe2 monolayer is still lacking. We have investigated the CDW of VTe2 monolayer by low energy electron diffraction (LEED) and scanning tunneling microscope (STM). While the LEED experiments revealed a (4X4) CDW transition at 192+-2 K, our low-temperature STM experiments resolved the (4X4) lattice distortions and charge-density modulation in real space, and further unveiled a 1D modulation that breaks the three-fold rotational and mirror symmetries in the CDW state. In accordance with the CDW state at low temperature, a CDW gap of 12 meV was detected by scanning tunneling spectroscopy (STS) at 4.9 K. Our work provides real-space evidence on the symmetry breaking of the (4X4) CDW state in VTe2 monolayer, and implies there is a certain mechanism, beyond the conventional Fermi surface nesting or the q-dependent electron-phonon coupling, is responsible for the formation of CDW state in VTe2 monolayer.

cond-mat.mtrl-sci↗

arXiv2019

Forward and Backward Knowledge Transfer for Sentiment Classification

This paper studies the problem of learning a sequence of sentiment classification tasks. The learned knowledge from each task is retained and used to help future or subsequent task learning. This learning paradigm is called Lifelong Learning (LL). However, existing LL methods either only transfer knowledge forward to help future learning and do not go back to improve the model of a previous task or require the training data of the previous task to retrain its model to exploit backward/reverse knowledge transfer. This paper studies reverse knowledge transfer of LL in the context of naive Bayesian (NB) classification. It aims to improve the model of a previous task by leveraging future knowledge without retraining using its training data. This is done by exploiting a key characteristic of the generative model of NB. That is, it is possible to improve the NB classifier for a task by improving its model parameters directly by using the retained knowledge from other tasks. Experimental results show that the proposed method markedly outperforms existing LL baselines.

cs.AI↗

arXiv2019

DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction

This paper focuses on two related subtasks of aspect-based sentiment analysis, namely aspect term extraction and aspect sentiment classification, which we call aspect term-polarity co-extraction. The former task is to extract aspects of a product or service from an opinion document, and the latter is to identify the polarity expressed in the document about these extracted aspects. Most existing algorithms address them as two separate tasks and solve them one by one, or only perform one task, which can be complicated for real applications. In this paper, we treat these two tasks as two sequence labeling problems and propose a novel Dual crOss-sharEd RNN framework (DOER) to generate all aspect term-polarity pairs of the input sentence simultaneously. Specifically, DOER involves a dual recurrent neural network to extract the respective representation of each task, and a cross-shared unit to consider the relationship between them. Experimental results demonstrate that the proposed framework outperforms state-of-the-art baselines on three benchmark datasets.

cs.CL↗

arXiv2019

GSN: A Graph-Structured Network for Multi-Party Dialogues

Existing neural models for dialogue response generation assume that utterances are sequentially organized. However, many real-world dialogues involve multiple interlocutors (i.e., multi-party dialogues), where the assumption does not hold as utterances from different interlocutors can occur "in parallel." This paper generalizes existing sequence-based models to a Graph-Structured neural Network (GSN) for dialogue modeling. The core of GSN is a graph-based encoder that can model the information flow along the graph-structured dialogues (two-party sequential dialogues are a special case). Experimental results show that GSN significantly outperforms existing sequence-based models.

cs.CL↗

arXiv2019

Spectral Perturbation Meets Incomplete Multi-view Data

Beyond existing multi-view clustering, this paper studies a more realistic clustering scenario, referred to as incomplete multi-view clustering, where a number of data instances are missing in certain views. To tackle this problem, we explore spectral perturbation theory. In this work, we show a strong link between perturbation risk bounds and incomplete multi-view clustering. That is, as the similarity matrix fed into spectral clustering is a quantity bounded in magnitude O(1), we transfer the missing problem from data to similarity and tailor a matrix completion method for incomplete similarity matrix. Moreover, we show that the minimization of perturbation risk bounds among different views maximizes the final fusion result across all views. This provides a solid fusion criteria for multi-view data. We motivate and propose a Perturbation-oriented Incomplete multi-view Clustering (PIC) method. Experimental results demonstrate the effectiveness of the proposed method.

cs.LG↗

arXiv2019

Controlled CNN-based Sequence Labeling for Aspect Extraction

One key task of fine-grained sentiment analysis on reviews is to extract aspects or features that users have expressed opinions on. This paper focuses on supervised aspect extraction using a modified CNN called controlled CNN (Ctrl). The modified CNN has two types of control modules. Through asynchronous parameter updating, it prevents over-fitting and boosts CNN's performance significantly. This model achieves state-of-the-art results on standard aspect extraction datasets. To the best of our knowledge, this is the first paper to apply control modules to aspect extraction.

cs.CL↗

arXiv2019

Tentative evidence of spatially extended GeV emission from SS433/W50

We analyze 10 years of Fermi-LAT data towards the SS433/W50 region. With the latest source catalog and diffuse background models, the gamma-ray excess from SS433/W50 is detected with a significance of 6σ in the photon energy range of 500 MeV - 10 GeV. Our analysis indicates that an extended flat disk morphology is preferred over a point-source description, suggesting that the GeV emission region is much larger than that of the TeV emission detected by HAWC. The size of the GeV emission is instead consistent with the extent of the radio nebula W50, a supernova remnant being distorted by the jets, so we suggest that the GeV emission may originate from this supernova remnant. The spectral result of the GeV emission is also consistent with an supernova remnant origin. We also derive the GeV flux upper limits on the TeV emission region, which put moderate constrains on the leptonic models to explain the multiwavelength data.

astro-ph.HE↗

arXiv2019

Improving Aspect Term Extraction with Bidirectional Dependency Tree Representation

Aspect term extraction is one of the important subtasks in aspect-based sentiment analysis. Previous studies have shown that using dependency tree structure representation is promising for this task. However, most dependency tree structures involve only one directional propagation on the dependency tree. In this paper, we first propose a novel bidirectional dependency tree network to extract dependency structure features from the given sentences. The key idea is to explicitly incorporate both representations gained separately from the bottom-up and top-down propagation on the given dependency syntactic tree. An end-to-end framework is then developed to integrate the embedded representations and BiLSTM plus CRF to learn both tree-structured and sequential features to solve the aspect term extraction problem. Experimental results demonstrate that the proposed model outperforms state-of-the-art baseline models on four benchmark SemEval datasets.

cs.CL↗