arXiv subjects

Ting Liu

Publications and source records attributed to Ting Liu.

411 records · Page 23Linked to original sources

arXiv2016

Effective LSTMs for Target-Dependent Sentiment Classification

Target-dependent sentiment classification remains a challenge: modeling the semantic relatedness of a target with its context words in a sentence. Different context words have different influences on determining the sentiment polarity of a sentence towards the target. Therefore, it is desirable to integrate the connections between target word and context words when building a learning system. In this paper, we develop two target dependent long short-term memory (LSTM) models, where target information is automatically taken into account. We evaluate our methods on a benchmark dataset from Twitter. Empirical results show that modeling sentence representation with standard LSTM does not perform well. Incorporating target information into LSTM can significantly boost the classification accuracy. The target-dependent LSTM models achieve state-of-the-art performances without using syntactic parser or external sentiment lexicons.

cs.CL↗

arXiv2016

Joint Learning of Siamese CNNs and Temporally Constrained Metrics for Tracklet Association

In this paper, we study the challenging problem of multi-object tracking in a complex scene captured by a single camera. Different from the existing tracklet association-based tracking methods, we propose a novel and efficient way to obtain discriminative appearance-based tracklet affinity models. Our proposed method jointly learns the convolutional neural networks (CNNs) and temporally constrained metrics. In our method, a Siamese convolutional neural network (CNN) is first pre-trained on the auxiliary data. Then the Siamese CNN and temporally constrained metrics are jointly learned online to construct the appearance-based tracklet affinity models. The proposed method can jointly learn the hierarchical deep features and temporally constrained segment-wise metrics under a unified framework. For reliable association between tracklets, a novel loss function incorporating temporally constrained multi-task learning mechanism is proposed. By employing the proposed method, tracklet association can be accomplished even in challenging situations. Moreover, a new dataset with 40 fully annotated sequences is created to facilitate the tracking evaluation. Experimental results on five public datasets and the new large-scale dataset show that our method outperforms several state-of-the-art approaches in multi-object tracking.

cs.CV↗

arXiv2016

Aspect Level Sentiment Classification with Deep Memory Network

We introduce a deep memory network for aspect level sentiment classification. Unlike feature-based SVM and sequential neural models such as LSTM, this approach explicitly captures the importance of each context word when inferring the sentiment polarity of an aspect. Such importance degree and text representation are calculated with multiple computational layers, each of which is a neural attention model over an external memory. Experiments on laptop and restaurant datasets demonstrate that our approach performs comparable to state-of-art feature based SVM system, and substantially better than LSTM and attention-based LSTM architectures. On both datasets we show that multiple computational layers could improve the performance. Moreover, our approach is also fast. The deep memory network with 9 layers is 15 times faster than LSTM with a CPU implementation.

cs.CL↗

arXiv2016

Learning to Start for Sequence to Sequence Architecture

The sequence to sequence architecture is widely used in the response generation and neural machine translation to model the potential relationship between two sentences. It typically consists of two parts: an encoder that reads from the source sentence and a decoder that generates the target sentence word by word according to the encoder's output and the last generated word. However, it faces to the cold start problem when generating the first word as there is no previous word to refer. Existing work mainly use a special start symbol to generate the first word. An obvious drawback of these work is that there is not a learnable relationship between words and the start symbol. Furthermore, it may lead to the error accumulation for decoding when the first word is incorrectly generated. In this paper, we proposed a novel approach to learning to generate the first word in the sequence to sequence architecture rather than using the start symbol. Experimental results on the task of response generation of short text conversation show that the proposed approach outperforms the state-of-the-art approach in both of the automatic and manual evaluations.

cs.CL↗

arXiv2016

SSHMT: Semi-supervised Hierarchical Merge Tree for Electron Microscopy Image Segmentation

Region-based methods have proven necessary for improving segmentation accuracy of neuronal structures in electron microscopy (EM) images. Most region-based segmentation methods use a scoring function to determine region merging. Such functions are usually learned with supervised algorithms that demand considerable ground truth data, which are costly to collect. We propose a semi-supervised approach that reduces this demand. Based on a merge tree structure, we develop a differentiable unsupervised loss term that enforces consistent predictions from the learned function. We then propose a Bayesian model that combines the supervised and the unsupervised information for probabilistic learning. The experimental results on three EM data sets demonstrate that by using a subset of only 3% to 7% of the entire ground truth data, our approach consistently performs close to the state-of-the-art supervised method with the full labeled data set, and significantly outperforms the supervised method with the same labeled subset.

cs.CV↗

arXiv2016

Game Theoretic Control of Multi-Agent Systems

Control of multi-agent systems via game theory is investigated. Assume a system level object is given, the utility functions for individual agents are designed to convert a multi-agent system into a potential game. First, for fixed topology, a necessary and sufficient condition is given to assure the existence of local information based utility functions. Then using local information the system can converge to a maximum point of the system object, which is a Nash equilibrium. It is also proved that a networked evolutionary potential game is a special case of this multi-agent system. Second, for time-varying topology, the state based potential game is utilized to design the optimal control. A strategy based Markov state transition process is proposed to assure the existence of state based potential function. As an extension of the fixed topology case, a necessary and sufficient condition for the existence of state depending utility functions using local information is also presented. It is also proved that using better reply with inertia strategy, the system converges to a maximum strategy of the state based system object, which is called the recurrent state equilibrium.

math.OC↗

arXiv2016

Image Segmentation Using Hierarchical Merge Tree

This paper investigates one of the most fundamental computer vision problems: image segmentation. We propose a supervised hierarchical approach to object-independent image segmentation. Starting with over-segmenting superpixels, we use a tree structure to represent the hierarchy of region merging, by which we reduce the problem of segmenting image regions to finding a set of label assignment to tree nodes. We formulate the tree structure as a constrained conditional model to associate region merging with likelihoods predicted using an ensemble boundary classifier. Final segmentations can then be inferred by finding globally optimal solutions to the model efficiently. We also present an iterative training and testing algorithm that generates various tree structures and combines them to emphasize accurate boundaries by segmentation accumulation. Experiment results and comparisons with other very recent methods on six public data sets demonstrate that our approach achieves the state-of-the-art region accuracy and is very competitive in image segmentation without semantic priors.

cs.CV↗

arXiv2016

Exploiting Multi-typed Treebanks for Parsing with Deep Multi-task Learning

Various treebanks have been released for dependency parsing. Despite that treebanks may belong to different languages or have different annotation schemes, they contain syntactic knowledge that is potential to benefit each other. This paper presents an universal framework for exploiting these multi-typed treebanks to improve parsing with deep multi-task learning. We consider two kinds of treebanks as source: the multilingual universal treebanks and the monolingual heterogeneous treebanks. Multiple treebanks are trained jointly and interacted with multi-level parameter sharing. Experiments on several benchmark datasets in various languages demonstrate that our approach can make effective use of arbitrary source treebanks to improve target parsing models.

cs.CL↗

arXiv2016

Generalized Turbo Signal Recovery for Nonlinear Measurements and Orthogonal Sensing Matrices

In this study, we propose a generalized turbo signal recovery algorithm to estimate a signal from quantized measurements, in which the sensing matrix is a row-orthogonal matrix, such as the partial discrete Fourier transform matrix. The state evolution of the proposed algorithm is derived and is shown to be consistent with that obtained with the replica method. Numerical experiments illustrate the excellent agreement of the proposed algorithm with theoretical state evolution.

cs.IT↗

arXiv2016

Exploring Segment Representations for Neural Segmentation Models

Many natural language processing (NLP) tasks can be generalized into segmentation problem. In this paper, we combine semi-CRF with neural network to solve NLP segmentation tasks. Our model represents a segment both by composing the input units and embedding the entire segment. We thoroughly study different composition functions and different segment embeddings. We conduct extensive experiments on two typical segmentation tasks: named entity recognition (NER) and Chinese word segmentation (CWS). Experimental results show that our neural semi-CRF model benefits from representing the entire segment and achieves the state-of-the-art performance on CWS benchmark dataset and competitive results on the CoNLL03 dataset.

cs.CL↗

arXiv2016

A Planning based Framework for Essay Generation

Generating an article automatically with computer program is a challenging task in artificial intelligence and natural language processing. In this paper, we target at essay generation, which takes as input a topic word in mind and generates an organized article under the theme of the topic. We follow the idea of text planning \cite{Reiter1997} and develop an essay generation framework. The framework consists of three components, including topic understanding, sentence extraction and sentence reordering. For each component, we studied several statistical algorithms and empirically compared between them in terms of qualitative or quantitative analysis. Although we run experiments on Chinese corpus, the method is language independent and can be easily adapted to other language. We lay out the remaining challenges and suggest avenues for future research.

cs.CL↗

arXiv2015

Video Tracking Using Learned Hierarchical Features

In this paper, we propose an approach to learn hierarchical features for visual object tracking. First, we offline learn features robust to diverse motion patterns from auxiliary video sequences. The hierarchical features are learned via a two-layer convolutional neural network. Embedding the temporal slowness constraint in the stacked architecture makes the learned features robust to complicated motion transformations, which is important for visual object tracking. Then, given a target video sequence, we propose a domain adaptation module to online adapt the pre-learned features according to the specific target object. The adaptation is conducted in both layers of the deep feature learning module so as to include appearance information of the specific target object. As a result, the learned hierarchical features can be robust to both complicated motion transformations and appearance changes of target objects. We integrate our feature learning algorithm into three tracking methods. Experimental results demonstrate that significant improvement can be achieved using our learned hierarchical features, especially on video sequences with complicated motion transformations.

cs.CV↗

arXiv2015

Heterodimer nanostructures induced energy focusing on metal film

As an interesting surface plasmon phenomenon discovered several years ago, electromagnetic field redistribution in nanoparticle dimer on film system provides a novel thought to enhance the light power on a plain film which could been widely used in surface enhanced Raman scattering (SERS), solar cells, photo-catalysis, etc. Homodimers on film are mainly investigated in past years, while the properties of heterodimers on film are still unclear. In this work, size difference induced electromagnetic field redistribution in Ag nanoparticle dimer on Au film system is investigated first. The results obtained from finite element method indicate that the smaller nanoparticle has much greater ability to focus light energy on Au film, which even reached more than 5 time compared to the larger one. Further researches indicate that this energy focusing ability has a strong relationship to the wavelength and diameter ration in dimer. Similar focusing phenomenon is found in the system of thick wire-smaller particle on film. Later, the SERS spectra collected in the small nanoparticle-large nanowire system provide an experimental evidence for this theoretic predication. Our results strengthen the understanding of surface plasmon on plane film and have potential application prospects in the surface plasmon related fields.

cond-mat.mes-hall↗

arXiv2014

Rare case of magnetic Ag$^{3+}$ ion: double perovskite Cs$_{2}$KAgF$_{6}$

Normally $4d$ or $5d$ transition metals are in a low-spin state. Here using first-principles calculations, we report on a rare case of a high-spin $S$=1 magnetic state for the Ag$^{3+}$ ion in the double perovskite Cs$_{2}$KAgF$_{6}$. We also explored a possibility of a conventional low-spin $S$=0 ground state and find an associated tetragonal distortion to be 0.29 Å. However, the lattice elastic energy cost and the Hund exchange loss exceed the e$_{g}$ crystal-field energy gain, thus making the low-spin tetragonal structure less favorable than the high-spin cubic structure. We conclude that the compact perovskite structure of Cs$_{2}$KAgF$_{6}$ is an important factor in stabilizing the unusual high-spin ground state of Ag$^{3+}$.

cond-mat.str-el↗

arXiv2014

Emotion Analysis Platform on Chinese Microblog

Weibo, as the largest social media service in China, has billions of messages generated every day. The huge number of messages contain rich sentimental information. In order to analyze the emotional changes in accordance with time and space, this paper presents an Emotion Analysis Platform (EAP), which explores the emotional distribution of each province, so that can monitor the global pulse of each province in China. The massive data of Weibo and the real-time requirements make the building of EAP challenging. In order to solve the above problems, emoticons, emotion lexicon and emotion-shifting rules are adopted in EAP to analyze the emotion of each tweet. In order to verify the effectiveness of the platform, case study on the Sichuan earthquake is done, and the analysis result of the platform accords with the fact. In order to analyze from quantity, we manually annotate a test set and conduct experiment on it. The experimental results show that the macro-Precision of EAP reaches 80% and the EAP works effectively.

cs.CL↗