arXiv subjects

Lihong Wang

Publications and source records attributed to Lihong Wang.

At least 37 records · Page 2Linked to original sources

arXiv2022

Attend and select: A segment selective transformer for microblog hashtag generation

Hashtag generation aims to generate short and informal topical tags from a microblog post, in which tokens or phrases form the hashtags. These tokens or phrases may originate from primary fragmental textual pieces (e.g., segments) in the original text and are separated into different segments. However, conventional sequence-to-sequence generation methods are hard to filter out secondary information from different textual granularity and are not good at selecting crucial tokens. Thus, they are suboptimal in generating more condensed hashtags. In this work, we propose a modified Transformer-based generation model with adding a segments-selection procedure for the original encoding and decoding phases. The segments-selection phase is based on a novel Segments Selection Mechanism (SSM) to model different textual granularity on global text, local segments, and tokens, contributing to generating condensed hashtags. Specifically, it first attends to primary semantic segments and then transforms discontinuous segments from the source text into a sequence of hashtags by selecting crucial tokens. Extensive evaluations on the two datasets reveal our approach's superiority with significant improvements to the extraction and generation baselines. The code and datasets are available at https://github.com/OpenSUM/HashtagGen.

cs.CL↗

arXiv2022

Event Extraction by Associating Event Types and Argument Roles

Event extraction (EE), which acquires structural event knowledge from texts, can be divided into two sub-tasks: event type classification and element extraction (namely identifying triggers and arguments under different role patterns). As different event types always own distinct extraction schemas (i.e., role patterns), previous work on EE usually follows an isolated learning paradigm, performing element extraction independently for different event types. It ignores meaningful associations among event types and argument roles, leading to relatively poor performance for less frequent types/roles. This paper proposes a novel neural association framework for the EE task. Given a document, it first performs type classification via constructing a document-level graph to associate sentence nodes of different types, and adopting a graph attention network to learn sentence embeddings. Then, element extraction is achieved by building a universal schema of argument roles, with a parameter inheritance mechanism to enhance role preference for extracted elements. As such, our model takes into account type and role associations during EE, enabling implicit information sharing among them. Experimental results show that our approach consistently outperforms most state-of-the-art EE methods in both sub-tasks. Particularly, for types/roles with less training data, the performance is superior to the existing methods.

cs.CL↗

arXiv2022

Music Influence Modeling Based on Directed Network Model

Studying the history of music may provide a glimpse into the development of human creativity as we examine the evolutionary and revolutionary trends in music and genres. First, a musical influence metric was created to construct a directed network of musical influence. Second, we examined the revolutions and development of musical genres, modeled the similarity, and explored similarities and influences within and between genres. Hierarchical cluster analysis and time series analysis of genres were used to explore the correlation between genres. Finally, Network Analysis, Semantic Analysis, and Random Forest Model are employed to find the revolutionaries. The above work was applied to Country music to sort out and analyze its evolution. In studying the connection between music and the social environment, time series analysis is used to determine the impact of social, political, or technological changes on music.

stat.AP↗

arXiv2021

Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relations

Event extraction is a fundamental task for natural language processing. Finding the roles of event arguments like event participants is essential for event extraction. However, doing so for real-life event descriptions is challenging because an argument's role often varies in different contexts. While the relationship and interactions between multiple arguments are useful for settling the argument roles, such information is largely ignored by existing approaches. This paper presents a better approach for event extraction by explicitly utilizing the relationships of event arguments. We achieve this through a carefully designed task-oriented dialogue system. To model the argument relation, we employ reinforcement learning and incremental learning to extract multiple arguments via a multi-turned, iterative process. Our approach leverages knowledge of the already extracted arguments of the same sentence to determine the role of arguments that would be difficult to decide individually. It then uses the newly obtained information to improve the decisions of previously extracted arguments. This two-way feedback process allows us to exploit the argument relations to effectively settle argument roles, leading to better sentence understanding and event extraction. Experimental results show that our approach consistently outperforms seven state-of-the-art event extraction methods for the classification of events and argument role and argument identification.

cs.CL↗

arXiv2021

Roadmap on Wavefront Shaping and deep imaging in complex media

The last decade has seen the development of a wide set of tools, such as wavefront shaping, computational or fundamental methods, that allow to understand and control light propagation in a complex medium, such as biological tissues or multimode fibers. A vibrant and diverse community is now working on this field, that has revolutionized the prospect of diffraction-limited imaging at depth in tissues. This roadmap highlights several key aspects of this fast developing field, and some of the challenges and opportunities ahead.

physics.optics↗

arXiv2021

HAWK: Rapid Android Malware Detection through Heterogeneous Graph Attention Networks

Android is undergoing unprecedented malicious threats daily, but the existing methods for malware detection often fail to cope with evolving camouflage in malware. To address this issue, we present HAWK, a new malware detection framework for evolutionary Android applications. We model Android entities and behavioural relationships as a heterogeneous information network (HIN), exploiting its rich semantic metastructures for specifying implicit higher-order relationships. An incremental learning model is created to handle the applications that manifest dynamically, without the need for re-constructing the whole HIN and the subsequent embedding model. The model can pinpoint rapidly the proximity between a new application and existing in-sample applications and aggregate their numerical embeddings under various semantics. Our experiments examine more than 80,860 malicious and 100,375 benign applications developed over a period of seven years, showing that HAWK achieves the highest detection accuracy against baselines and takes only 3.5ms on average to detect an out-of-sample application, with the accelerated training time of 50x faster than the existing approach.

cs.CR↗

arXiv2021

CasEE: A Joint Learning Framework with Cascade Decoding for Overlapping Event Extraction

Event extraction (EE) is a crucial information extraction task that aims to extract event information in texts. Most existing methods assume that events appear in sentences without overlaps, which are not applicable to the complicated overlapping event extraction. This work systematically studies the realistic event overlapping problem, where a word may serve as triggers with several types or arguments with different roles. To tackle the above problem, we propose a novel joint learning framework with cascade decoding for overlapping event extraction, termed as CasEE. Particularly, CasEE sequentially performs type detection, trigger extraction and argument extraction, where the overlapped targets are extracted separately conditioned on the specific former prediction. All the subtasks are jointly learned in a framework to capture dependencies among the subtasks. The evaluation on a public event extraction benchmark FewFC demonstrates that CasEE achieves significant improvements on overlapping event extraction over previous competitive methods.

cs.CL↗

arXiv2020

Adaptive Attentional Network for Few-Shot Knowledge Graph Completion

Few-shot Knowledge Graph (KG) completion is a focus of current research, where each task aims at querying unseen facts of a relation given its few-shot reference entity pairs. Recent attempts solve this problem by learning static representations of entities and references, ignoring their dynamic properties, i.e., entities may exhibit diverse roles within task relations, and references may make different contributions to queries. This work proposes an adaptive attentional network for few-shot KG completion by learning adaptive entity and reference representations. Specifically, entities are modeled by an adaptive neighbor encoder to discern their task-oriented roles, while references are modeled by an adaptive query-aware aggregator to differentiate their contributions. Through the attention mechanism, both entities and references can capture their fine-grained semantic meanings, and thus render more expressive representations. This will be more predictive for knowledge acquisition in the few-shot scenario. Evaluation in link prediction on two public datasets shows that our approach achieves new state-of-the-art results with different few-shot sizes.

cs.CL↗

arXiv2020

Heuristic Semi-Supervised Learning for Graph Generation Inspired by Electoral College

Recently, graph-based algorithms have drawn much attention because of their impressive success in semi-supervised setups. For better model performance, previous studies learn to transform the topology of the input graph. However, these works only focus on optimizing the original nodes and edges, leaving the direction of augmenting existing data unexplored. In this paper, by simulating the generation process of graph signals, we propose a novel heuristic pre-processing technique, namely ELectoral COllege (ELCO), which automatically expands new nodes and edges to refine the label similarity within a dense subgraph. Substantially enlarging the original training set with high-quality generated labeled data, our framework can effectively benefit downstream models. To justify the generality and practicality of ELCO, we couple it with the popular Graph Convolution Network and Graph Attention Network to perform extensive evaluations on three standard datasets. In all setups tested, our method boosts the average score of base models by a large margin of 4.7 points, as well as consistently outperforms the state-of-the-art. We release our code and data on https://github.com/RingBDStack/ELCO to guarantee reproducibility.

cs.SI↗

arXiv2020

Modeling relation paths for knowledge base completion via joint adversarial training

Knowledge Base Completion (KBC), which aims at determining the missing relations between entity pairs, has received increasing attention in recent years. Most existing KBC methods focus on either embedding the Knowledge Base (KB) into a specific semantic space or leveraging the joint probability of Random Walks (RWs) on multi-hop paths. Only a few unified models take both semantic and path-related features into consideration with adequacy. In this paper, we propose a novel method to explore the intrinsic relationship between the single relation (i.e. 1-hop path) and multi-hop paths between paired entities. We use Hierarchical Attention Networks (HANs) to select important relations in multi-hop paths and encode them into low-dimensional vectors. By treating relations and multi-hop paths as two different input sources, we use a feature extractor, which is shared by two downstream components (i.e. relation classifier and source discriminator), to capture shared/similar information between them. By joint adversarial training, we encourage our model to extract features from the multi-hop paths which are representative for relation completion. We apply the trained model (except for the source discriminator) to several large-scale KBs for relation completion. Experimental results show that our method outperforms existing path information-based approaches. Since each sub-module of our model can be well interpreted, our model can be applied to a large number of relation learning tasks.

cs.AI↗

arXiv2020

SIR Model-based Prediction of Infected Population of Coronavirus in Hubei Province

After the sudden outbreak of Coronavirus in Wuhan, continuous and rich data of the epidemic has been made public as the vital fact for decision support in control measures and aggressive implementation of containment strategies and plans. With the further growth and spreading of the virus, future resource allocation and planning under updated strategies and measures rely on careful study of the epidemic data and characteristics for accurate prediction and estimation. By using the SIR model and reported data, key parameters are obtained from least sum of squared errors for an accurate prediction of epidemic trend in the last four weeks.

q-bio.PE↗

arXiv2019

Dynamic Network Embedding via Incremental Skip-gram with Negative Sampling

Network representation learning, as an approach to learn low dimensional representations of vertices, has attracted considerable research attention recently. It has been proven extremely useful in many machine learning tasks over large graph. Most existing methods focus on learning the structural representations of vertices in a static network, but cannot guarantee an accurate and efficient embedding in a dynamic network scenario. To address this issue, we present an efficient incremental skip-gram algorithm with negative sampling for dynamic network embedding, and provide a set of theoretical analyses to characterize the performance guarantee. Specifically, we first partition a dynamic network into the updated, including addition/deletion of links and vertices, and the retained networks over time. Then we factorize the objective function of network embedding into the added, vanished and retained parts of the network. Next we provide a new stochastic gradient-based method, guided by the partitions of the network, to update the nodes and the parameter vectors. The proposed algorithm is proven to yield an objective function value with a bounded difference to that of the original objective function. Experimental results show that our proposal can significantly reduce the training time while preserving the comparable performance. We also demonstrate the correctness of the theoretical analysis and the practical usefulness of the dynamic network embedding. We perform extensive experiments on multiple real-world large network datasets over multi-label classification and link prediction tasks to evaluate the effectiveness and efficiency of the proposed framework, and up to 22 times speedup has been achieved.

cs.LG↗

arXiv2019

Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text Classification

CNNs, RNNs, GCNs, and CapsNets have shown significant insights in representation learning and are widely used in various text mining tasks such as large-scale multi-label text classification. However, most existing deep models for multi-label text classification consider either the non-consecutive and long-distance semantics or the sequential semantics, but how to consider them both coherently is less studied. In addition, most existing methods treat output labels as independent methods, but ignore the hierarchical relations among them, leading to useful semantic information loss. In this paper, we propose a novel hierarchical taxonomy-aware and attentional graph capsule recurrent CNNs framework for large-scale multi-label text classification. Specifically, we first propose to model each document as a word order preserved graph-of-words and normalize it as a corresponding words-matrix representation which preserves both the non-consecutive, long-distance and local sequential semantics. Then the words-matrix is input to the proposed attentional graph capsule recurrent CNNs for more effectively learning the semantic features. To leverage the hierarchical relations among the class labels, we propose a hierarchical taxonomy embedding method to learn their representations, and define a novel weighted margin loss by incorporating the label representation similarity. Extensive evaluations on three datasets show that our model significantly improves the performance of large-scale multi-label text classification by comparing with state-of-the-art approaches.

cs.IR↗

arXiv2019

Two-dimensional rogue waves on zero background of the Davey-Stewartson II equation

A prototypical example of a rogue wave structure in a two-dimensional model is presented in the context of the Davey-Stewartson~II (DS~II) equation arising in water waves. The analytical methodology involves a Taylor expansion of an eigenfunctionof the model's Lax pair which is used to form a hierarchy of infinitely many new eigenfunctions. These are used for the construction of two-dimensional (2D) rogue waves (RWs) of the DS~II equation by the even-fold Darboux transformation (DT). The obtained 2D RWs, which are localized in both space and time, can be viewed as a 2D analogue of the Peregrine soliton and are thus natural candidates to describe oceanic RW phenomena,as well as ones in 2D fluid systems and water tanks.

nlin.SI↗

arXiv2018

Inferring Multiplex Diffusion Network via Multivariate Marked Hawkes Process

Understanding the diffusion in social network is an important task. However, this task is challenging since (1) the network structure is usually hidden with only observations of events like "post" or "repost" associated with each node, and (2) the interactions between nodes encompass multiple distinct patterns which in turn affect the diffusion patterns. For instance, social interactions seldom develop on a single channel, and multiple relationships can bind pairs of people due to their various common interests. Most previous work considers only one of these two challenges which is apparently unrealistic. In this paper, we study the problem of \emph{inferring multiplex network} in social networks. We propose the Multiplex Diffusion Model (MDM) which incorporates the multivariate marked Hawkes process and topic model to infer the multiplex structure of social network. A MCMC based algorithm is developed to infer the latent multiplex structure and to estimate the node-related parameters. We evaluate our model based on both synthetic and real-world datasets. The results show that our model is more effective in terms of uncovering the multiplex network structure.

cs.SI↗

arXiv2017

Knowledge Graph Embedding with Iterative Guidance from Soft Rules

Embedding knowledge graphs (KGs) into continuous vector spaces is a focus of current research. Combining such an embedding model with logic rules has recently attracted increasing attention. Most previous attempts made a one-time injection of logic rules, ignoring the interactive nature between embedding learning and logical inference. And they focused only on hard rules, which always hold with no exception and usually require extensive manual effort to create or validate. In this paper, we propose Rule-Guided Embedding (RUGE), a novel paradigm of KG embedding with iterative guidance from soft rules. RUGE enables an embedding model to learn simultaneously from 1) labeled triples that have been directly observed in a given KG, 2) unlabeled triples whose labels are going to be predicted iteratively, and 3) soft rules with various confidence levels extracted automatically from the KG. In the learning process, RUGE iteratively queries rules to obtain soft labels for unlabeled triples, and integrates such newly labeled triples to update the embedding model. Through this iterative procedure, knowledge embodied in logic rules may be better transferred into the learned embeddings. We evaluate RUGE in link prediction on Freebase and YAGO. Experimental results show that: 1) with rule knowledge injected iteratively, RUGE achieves significant and consistent improvements over state-of-the-art baselines; and 2) despite their uncertainties, automatically extracted soft rules are highly beneficial to KG embedding, even those with moderate confidence levels. The code and data used for this paper can be obtained from https://github.com/iieir-km/RUGE.

cs.AI↗

arXiv2017

Construction of rational solutions of the real modified Korteweg-de Vries equation from its periodic solutions

In this paper, we consider the real modified Korteweg-de Vries (mKdV) equation and construct a special kind of breather solution, which can be obtained by taking the limit $λ_{j}$ $\rightarrow$ $λ_{1}$ of the Lax pair eigenvalues used in the $n$-fold Darboux transformation that generates the order-$n$ periodic solution from a constant seed solution. Further, this special kind of breather solution of order $n$ can be used to generate the order-$n$ rational solution by taking the limit $λ_{1}$ $\rightarrow$ $λ_{0}$, where $λ_{0}$ is a special eigenvalue associated to the eigenfunction $ϕ$ of the Lax pair of the mKdV equation. This eigenvalue $λ_0$, for which $ϕ(λ_0)=0$, corresponds to the limit of infinite period of the periodic solution. %This second limit of double eigenvalue degeneration might be realized approximately in optical fibers, in which an injected %initial ideal pulse is created by a comb system and a programmable optical filter according to the profile of the analytical %form of the b-positon at a certain spatial position $x_{0}$. Therefore, we suggest a new way to observe the higher-order %rational solutions in optical fibers, namely, to measure the wave patterns at the central region of the higher order b-positon %generated by ideal initial pulses when the eigenvalue $λ_{1}$ is approaching $λ_{0}$. Our analytical and numerical results show the effective mechanism of generation of higher-order rational solutions of the mKdV equation from the double eigenvalue degeneration process of multi-periodic solutions.

nlin.SI↗

arXiv2017

Generation of higher-order rogue waves from multi-breathers by double degeneracy in an optical fibre

In this paper, we construct a special kind of breather solution of the nonlinear Schrödinger (NLS) equation, the so-called breather-positon ({\it b-positon} for short), which can be obtained by taking the limit $λ_{j}$ $\rightarrow$ $λ_{1}$ of the Lax pair eigenvalues in the order-$n$ periodic solution which is generated by the $n$-fold Darboux transformation from a special "seed" solution--plane wave. Further, an order-$n$ {\it b-positon} gives an order-$n$ rogue wave under a limit $λ_1\rightarrow λ_0$. Here $λ_0$ is a special eigenvalue in a breather of the NLS equation such that its period goes to infinity. Several analytical plots of order-2 breather confirm visually this double degeneration. The last limit in this double degeneration can be realized approximately in an optical fiber governed by the NLS equation, in which an injected initial ideal pulse is created by a frequency comb system and a programable optical filter (wave shaper) according to the profile of an analytical form of the {\it b-positon} at a certain position $z_0$. We also suggest a new way to observe higher-order rogue waves generation in an optical fiber, namely, measure the patterns at the central region of the higher-order {\it b-positon} generated by above ideal initial pulses when $λ_1$ is very close to the $λ_0$. The excellent agreement between the numerical solutions generated from initial ideal inputs with a low signal noise ratio and analytical solutions of order-2 {\it b-positon}, supports strongly this way in a realistic optical fiber system. Our results also show the validity of the generating mechanism of a higher-order rogue waves from a multi-breathers through the double degeneration.

nlin.SI↗