arXiv subjects

Zhiguo Wang

Publications and source records attributed to Zhiguo Wang.

At least 91 records · Page 5Linked to original sources

arXiv2019

Dual Set Membership Filter with Minimizing Nonlinear Transformation of Ellipsoid

In this paper, we propose a dual set membership filter for nonlinear dynamic systems with unknown but bounded noises, and it has three distinctive properties. Firstly, the nonlinear system is translated into the linear system by leveraging a semi-infinite programming, rather than linearizing the nonlinear function. In fact, the semi-infinite programming is to find an ellipsoid bounding the nonlinear transformation of an ellipsoid, which aims to compute a tight ellipsoid to cover the state. Secondly, the duality result of the semi-infinite programming is derived by a rigorous analysis, then a first order Frank-Wolfe method is developed to efficiently solve it with a lower computation complexity. Thirdly, the proposed filter can take advantage of the linear set membership filter framework and can work on-line without solving the semidefinite programming problem. Furthermore, we apply the dual set membership filter to a typical scenario of mobile robot localization. Finally, two illustrative examples in the simulations show the advantages and effectiveness of the dual set membership filter.

math.DS↗

arXiv2019

Semantic Neural Machine Translation using AMR

It is intuitive that semantic representations can be useful for machine translation, mainly because they can help in enforcing meaning preservation and handling data sparsity (many sentences correspond to one meaning) of machine translation models. On the other hand, little work has been done on leveraging semantics for neural machine translation (NMT). In this work, we study the usefulness of AMR (short for abstract meaning representation) on NMT. Experiments on a standard English-to-German dataset show that incorporating AMR as additional knowledge can significantly improve a strong attention-based sequence-to-sequence neural translation model.

cs.CL↗

arXiv2019

SQL-to-Text Generation with Graph-to-Sequence Model

Previous work approaches the SQL-to-text generation task using vanilla Seq2Seq models, which may not fully capture the inherent graph-structured information in SQL query. In this paper, we first introduce a strategy to represent the SQL query as a directed graph and then employ a graph-to-sequence model to encode the global structure information into node embeddings. This model can effectively learn the correlation between the SQL query pattern and its interpretation. Experimental results on the WikiSQL dataset and Stackoverflow dataset show that our model significantly outperforms the Seq2Seq and Tree2Seq baselines, achieving the state-of-the-art performance.

cs.CL↗

arXiv2018

Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks

The celebrated Sequence to Sequence learning (Seq2Seq) technique and its numerous variants achieve excellent performance on many tasks. However, many machine learning tasks have inputs naturally represented as graphs; existing Seq2Seq models face a significant challenge in achieving accurate conversion from graph form to the appropriate sequence. To address this challenge, we introduce a novel general end-to-end graph-to-sequence neural encoder-decoder model that maps an input graph to a sequence of vectors and uses an attention-based LSTM method to decode the target sequence from these vectors. Our method first generates the node and graph embeddings using an improved graph-based neural network with a novel aggregation strategy to incorporate edge direction information in the node embeddings. We further introduce an attention mechanism that aligns node embeddings and the decoding sequence to better cope with large graphs. Experimental results on bAbI, Shortest Path, and Natural Language Generation tasks demonstrate that our model achieves state-of-the-art performance and significantly outperforms existing graph neural networks, Seq2Seq, and Tree2Seq models; using the proposed bi-directional node embedding aggregation strategy, the model can converge rapidly to the optimal performance.

cs.AI↗

arXiv2018

Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks

Multi-hop reading comprehension focuses on one type of factoid question, where a system needs to properly integrate multiple pieces of evidence to correctly answer a question. Previous work approximates global evidence with local coreference information, encoding coreference chains with DAG-styled GRU layers within a gated-attention reader. However, coreference is limited in providing information for rich inference. We introduce a new method for better connecting global evidence, which forms more complex graphs compared to DAGs. To perform evidence integration on our graphs, we investigate two recent graph neural networks, namely graph convolutional network (GCN) and graph recurrent network (GRN). Experiments on two standard datasets show that richer global information leads to better answers. Our method performs better than all published results on these datasets.

cs.CL↗

arXiv2018

A Unified Query-based Generative Model for Question Generation and Question Answering

We propose a query-based generative model for solving both tasks of question generation (QG) and question an- swering (QA). The model follows the classic encoder- decoder framework. The encoder takes a passage and a query as input then performs query understanding by matching the query with the passage from multiple per- spectives. The decoder is an attention-based Long Short Term Memory (LSTM) model with copy and coverage mechanisms. In the QG task, a question is generated from the system given the passage and the target answer, whereas in the QA task, the answer is generated given the question and the passage. During the training stage, we leverage a policy-gradient reinforcement learning algorithm to overcome exposure bias, a major prob- lem resulted from sequence learning with cross-entropy loss. For the QG task, our experiments show higher per- formances than the state-of-the-art results. When used as additional training data, the automatically generated questions even improve the performance of a strong ex- tractive QA system. In addition, our model shows bet- ter performance than the state-of-the-art baselines of the generative QA task.

cs.CL↗

arXiv2018

N-ary Relation Extraction using Graph State LSTM

Cross-sentence $n$-ary relation extraction detects relations among $n$ entities across multiple sentences. Typical methods formulate an input as a \textit{document graph}, integrating various intra-sentential and inter-sentential dependencies. The current state-of-the-art method splits the input graph into two DAGs, adopting a DAG-structured LSTM for each. Though being able to model rich linguistic knowledge by leveraging graph edges, important information can be lost in the splitting procedure. We propose a graph-state LSTM model, which uses a parallel state to model each word, recurrently enriching state values via message passing. Compared with DAG LSTMs, our graph LSTM keeps the original graph structure, and speeds up computation by allowing more parallelization. On a standard benchmark, our model shows the best result in the literature.

cs.CL↗

arXiv2018

A Graph-to-Sequence Model for AMR-to-Text Generation

The problem of AMR-to-text generation is to recover a text representing the same meaning as an input AMR graph. The current state-of-the-art method uses a sequence-to-sequence model, leveraging LSTM for encoding a linearized AMR structure. Although being able to model non-local semantic information, a sequence LSTM can lose information from the AMR graph structure, and thus faces challenges with large graphs, which result in long sequences. We introduce a neural graph-to-sequence model, using a novel LSTM structure for directly encoding graph-level semantics. On a standard benchmark, our model shows superior results to existing methods in the literature.

cs.CL↗

arXiv2018

Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model

Existing neural semantic parsers mainly utilize a sequence encoder, i.e., a sequential LSTM, to extract word order features while neglecting other valuable syntactic information such as dependency graph or constituent trees. In this paper, we first propose to use the \textit{syntactic graph} to represent three types of syntactic information, i.e., word order, dependency and constituency features. We further employ a graph-to-sequence model to encode the syntactic graph and decode a logical form. Experimental results on benchmark datasets show that our model is comparable to the state-of-the-art on Jobs640, ATIS and Geo880. Experimental results on adversarial examples demonstrate the robustness of the model is also improved by encoding more syntactic information.

cs.CL↗

arXiv2018

Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering

A popular recent approach to answering open-domain questions is to first search for question-related passages and then apply reading comprehension models to extract answers. Existing methods usually extract answers from single passages independently. But some questions require a combination of evidence from across different sources to answer correctly. In this paper, we propose two models which make use of multiple passages to generate their answers. Both use an answer-reranking approach which reorders the answer candidates generated by an existing state-of-the-art QA model. We propose two methods, namely, strength-based re-ranking and coverage-based re-ranking, to make use of the aggregated evidence from different passages to better determine the answer. Our models have achieved state-of-the-art results on three public open-domain QA datasets: Quasar-T, SearchQA and the open-domain version of TriviaQA, with about 8 percentage points of improvement over the former two datasets.

cs.CL↗

arXiv2018

Knowledge Base Relation Detection via Multi-View Matching

Relation detection is a core component for Knowledge Base Question Answering (KBQA). In this paper, we propose a KB relation detection model via multi-view matching which utilizes more useful information extracted from question and KB. The matching inside each view is through multiple perspectives to compare two input texts thoroughly. All these components are designed in an end-to-end trainable neural network model. Experiments on SimpleQuestions and WebQSP yield state-of-the-art results.

cs.AI↗

arXiv2018

On Equivalence and Computational Efficiency of the Major Relaxation Methods for Minimum Ellipsoid Containing the Intersection of Ellipsoids

This paper investigates the problem on the minimum ellipsoid containing the intersection of multiple ellipsoids, which has been extensively applied to information science, target tracking and data fusion etc. There are three major relaxation methods involving SDP relaxation, S-procedure relaxation and bounding ellipsoid relaxation, which are derived by different ideas or viewpoints. However, it is unclear for the interrelationships among these methods. This paper reveals the equivalence among the three relaxation methods by three stages. Firstly, the SDP relaxation method can be equivalently simplified to a decoupled SDP relaxation method. Secondly, the equivalence between the SDP relaxation method and the S-procedure relaxation method can be obtained by rigorous analysis. Thirdly, we establish the equivalence between the decoupled SDP relaxation method and the bounding ellipsoid relaxation method. Therefore, the three relaxation methods are unified through the decoupled SDP relaxation method. By analysis of the computational complexity, the decoupled SDP relaxation method has the least computational burden among the three methods. The above results are helpful for the research of set-membership filter and distributed estimation fusion. Finally, the performance of each method is evaluated by some typical numerical examples in information fusion and filtering.

math.OC↗

arXiv2017

R$^3$: Reinforced Reader-Ranker for Open-Domain Question Answering

In recent years researchers have achieved considerable success applying neural network methods to question answering (QA). These approaches have achieved state of the art results in simplified closed-domain settings such as the SQuAD (Rajpurkar et al., 2016) dataset, which provides a pre-selected passage, from which the answer to a given question may be extracted. More recently, researchers have begun to tackle open-domain QA, in which the model is given a question and access to a large corpus (e.g., wikipedia) instead of a pre-selected passage (Chen et al., 2017a). This setting is more complex as it requires large-scale search for relevant passages by an information retrieval component, combined with a reading comprehension model that "reads" the passages to generate an answer to the question. Performance in this setting lags considerably behind closed-domain performance. In this paper, we present a novel open-domain QA system called Reinforced Ranker-Reader $(R^3)$, based on two algorithmic innovations. First, we propose a new pipeline for open-domain QA with a Ranker component, which learns to rank retrieved passages in terms of likelihood of generating the ground-truth answer to a given question. Second, we propose a novel method that jointly trains the Ranker along with an answer-generation Reader model, based on reinforcement learning. We report extensive experimental results showing that our method significantly improves on the state of the art for multiple open-domain QA datasets.

cs.CL↗

arXiv2017

Asymptotic spreading speed for the weak competition system with a free boundary

This paper is concerned with a diffusive Lotka-Volterra type competition system with a free boundary in one space dimension. Such a system may be used to describe the invasion of a new species into the habitat of a native competitor. We show that the longtime dynamical behavior of the system is determined by a spreading-vanishing dichotomy, and provide sharp criteria for spreading and vanishing of the invasive species. Moreover, we determine the asymptotic spreading speed of the invasive species when its spreading is successful, which involves two systems of traveling wave type equations, and is highly nontrivial to establish.

math.AP↗

arXiv2017

$k$-Nearest Neighbor Augmented Neural Networks for Text Classification

In recent years, many deep-learning based models are proposed for text classification. This kind of models well fits the training set from the statistical point of view. However, it lacks the capacity of utilizing instance-level information from individual instances in the training set. In this work, we propose to enhance neural network models by allowing them to leverage information from $k$-nearest neighbor (kNN) of the input text. Our model employs a neural network that encodes texts into text embeddings. Moreover, we also utilize $k$-nearest neighbor of the input text as an external memory, and utilize it to capture instance-level information from the training set. The final prediction is made based on features from both the neural network encoder and the kNN memory. Experimental results on several standard benchmark datasets show that our model outperforms the baseline model on all the datasets, and it even beats a very deep neural network model (with 29 layers) in several datasets. Our model also shows superior performance when training instances are scarce, and when the training set is severely unbalanced. Our model also leverages techniques such as semi-supervised training and transfer learning quite well.

cs.CL↗

arXiv2017

Preconditioned wire array Z-pinches driven by a double pulse current generator

Suppressing of the core-corona structures shows a strong potential as a new breakthrough in the X-ray power production of the wire array Z-pinches. In this letter, the demonstration of suppressing the core-corona structures and its ablation using a novel double pulse current generator "Qin-1" facility is presented. The "Qin-1" facility coupled a ~10 kA 20 ns prepulse generator to a ~ 1 MA 170 ns main current generator. Driven by the prepulse current, the two aluminum wire array were mostly heated to gaseous state rather than the core-corona structures, and the implosion of the aluminum vapors driven by the main current showed no ablation, and no trailing mass. The seeds for the MRT instability formed from the inhomogeneous ablation were suppressed, however, the magneto Rayleigh-Taylor instability during the implosion was still significant and further researches on the generation and development of the magneto Rayleigh-Taylor instabilities of this gasified wire array are needed.

physics.plasm-ph↗

arXiv2017

Semi-supervised Clustering for Short Text via Deep Representation Learning

In this work, we propose a semi-supervised method for short text clustering, where we represent texts as distributed vectors with neural networks, and use a small amount of labeled data to specify our intention for clustering. We design a novel objective to combine the representation learning process and the k-means clustering process together, and optimize the objective with both labeled data and unlabeled data iteratively until convergence through three steps: (1) assign each short text to its nearest centroid based on its representation from the current neural networks; (2) re-estimate the cluster centroids based on cluster assignments from step (1); (3) update neural networks according to the objective by keeping centroids and cluster assignments fixed. Experimental results on four datasets show that our method works significantly better than several other text clustering methods.

cs.CL↗

arXiv2017

Sentence Similarity Learning by Lexical Decomposition and Composition

Most conventional sentence similarity methods only focus on similar parts of two input sentences, and simply ignore the dissimilar parts, which usually give us some clues and semantic meanings about the sentences. In this work, we propose a model to take into account both the similarities and dissimilarities by decomposing and composing lexical semantics over sentences. The model represents each word as a vector, and calculates a semantic matching vector for each word based on all words in the other sentence. Then, each word vector is decomposed into a similar component and a dissimilar component based on the semantic matching vector. After this, a two-channel CNN model is employed to capture features by composing the similar and dissimilar components. Finally, a similarity score is estimated over the composed feature vectors. Experimental results show that our model gets the state-of-the-art performance on the answer sentence selection task, and achieves a comparable result on the paraphrase identification task.

cs.CL↗