arXiv subjects

Zhefeng Wang

Publications and source records attributed to Zhefeng Wang.

48 records · Page 3Linked to original sources

arXiv2022

JABER and SABER: Junior and Senior Arabic BERt

Language-specific pre-trained models have proven to be more accurate than multilingual ones in a monolingual evaluation setting, Arabic is no exception. However, we found that previously released Arabic BERT models were significantly under-trained. In this technical report, we present JABER and SABER, Junior and Senior Arabic BERt respectively, our pre-trained language model prototypes dedicated for Arabic. We conduct an empirical study to systematically evaluate the performance of models across a diverse set of existing Arabic NLU tasks. Experimental results show that JABER and SABER achieve state-of-the-art performances on ALUE, a new benchmark for Arabic Language Understanding Evaluation, as well as on a well-established NER benchmark.

cs.CL↗

arXiv2021

An In-depth Study on Internal Structure of Chinese Words

Unlike English letters, Chinese characters have rich and specific meanings. Usually, the meaning of a word can be derived from its constituent characters in some way. Several previous works on syntactic parsing propose to annotate shallow word-internal structures for better utilizing character-level information. This work proposes to model the deep internal structures of Chinese words as dependency trees with 11 labels for distinguishing syntactic relationships. First, based on newly compiled annotation guidelines, we manually annotate a word-internal structure treebank (WIST) consisting of over 30K multi-char words from Chinese Penn Treebank. To guarantee quality, each word is independently annotated by two annotators and inconsistencies are handled by a third senior annotator. Second, we present detailed and interesting analysis on WIST to reveal insights on Chinese word formation. Third, we propose word-internal structure parsing as a new task, and conduct benchmark experiments using a competitive dependency parser. Finally, we present two simple ways to encode word-internal structures, leading to promising gains on the sentence-level syntactic parsing task.

cs.CL↗

arXiv2021

Read, Retrospect, Select: An MRC Framework to Short Text Entity Linking

Entity linking (EL) for the rapidly growing short text (e.g. search queries and news titles) is critical to industrial applications. Most existing approaches relying on adequate context for long text EL are not effective for the concise and sparse short text. In this paper, we propose a novel framework called Multi-turn Multiple-choice Machine reading comprehension (M3}) to solve the short text EL from a new perspective: a query is generated for each ambiguous mention exploiting its surrounding context, and an option selection module is employed to identify the golden entity from candidates using the query. In this way, M3 framework sufficiently interacts limited context with candidate entities during the encoding process, as well as implicitly considers the dissimilarities inside the candidate bunch in the selection stage. In addition, we design a two-stage verifier incorporated into M3 to address the commonly existed unlinkable problem in short text. To further consider the topical coherence and interdependence among referred entities, M3 leverages a multi-turn fashion to deal with mentions in a sequence manner by retrospecting historical cues. Evaluation shows that our M3 framework achieves the state-of-the-art performance on five Chinese and English datasets for the real-world short text EL.

cs.CL↗

arXiv2019

Finding Route Hotspots in Large Labeled Networks

In many advanced network analysis applications, like social networks, e-commerce, and network security, hotspots are generally considered as a group of vertices that are tightly connected owing to the similar characteristics, such as common habits and location proximity. In this paper, we investigate the formation of hotspots from an alternative perspective that considers the routes along the network paths as the auxiliary information, and attempt to find the route hotspots in large labeled networks. A route hotspot is a cohesive subgraph that is covered by a set of routes, and these routes correspond to the same sequential pattern consisting of vertices' labels. To the best of our knowledge, the problem of Finding Route Hotspots in Large Labeled Networks has not been tackled in the literature. However, it is challenging as counting the number of hotspots in a network is #P-hard. Inspired by the observation that the sizes of hotspots decrease with the increasing lengths of patterns, we prove several anti-monotonicity properties of hotspots, and then develop a scalable algorithm called FastRH that can use these properties to effectively prune the patterns that cannot form any hotspots. In addition, to avoid the duplicate computation overhead, we judiciously design an effective index structure called RH-Index for storing the hotspot and pattern information collectively, which also enables incremental updating and efficient query processing. Our experimental results on real-world datasets clearly demonstrate the effectiveness and scalability of our proposed methods.

cs.DS↗

arXiv2019

Finding Theme Communities from Database Networks

Given a database network where each vertex is associated with a transaction database, we are interested in finding theme communities. Here, a theme community is a cohesive subgraph such that a common pattern is frequent in all transaction databases associated with the vertices in the subgraph. Finding all theme communities from a database network enjoys many novel applications. However, it is challenging since even counting the number of all theme communities in a database network is #P-hard. Inspired by the observation that a theme community shrinks when the length of the pattern increases, we investigate several properties of theme communities and develop TCFI, a scalable algorithm that uses these properties to effectively prune the patterns that cannot form any theme community. We also design TC-Tree, a scalable algorithm that decomposes and indexes theme communities efficiently. Retrieving a ranked list of theme communities from a TC-Tree of hundreds of millions of theme communities takes less than 1 second. Extensive experiments and a case study demonstrate the effectiveness and scalability of TCFI and TC-Tree in discovering and querying meaningful theme communities from large database networks.

cs.DB↗

arXiv2018

Robust Estimation of Similarity Transformation for Visual Object Tracking

Most of existing correlation filter-based tracking approaches only estimate simple axis-aligned bounding boxes, and very few of them is capable of recovering the underlying similarity transformation. To tackle this challenging problem, in this paper, we propose a new correlation filter-based tracker with a novel robust estimation of similarity transformation on the large displacements. In order to efficiently search in such a large 4-DoF space in real-time, we formulate the problem into two 2-DoF sub-problems and apply an efficient Block Coordinates Descent solver to optimize the estimation result. Specifically, we employ an efficient phase correlation scheme to deal with both scale and rotation changes simultaneously in log-polar coordinates. Moreover, a variant of correlation filter is used to predict the translational motion individually. Our experimental results demonstrate that the proposed tracker achieves very promising prediction performance compared with the state-of-the-art visual object tracking methods while still retaining the advantages of high efficiency and simplicity in conventional correlation filter-based tracking methods.

cs.CV↗

arXiv2018

Mining Top-k Sequential Patterns in Database Graphs:A New Challenging Problem and a Sampling-based Approach

In many real world networks, a vertex is usually associated with a transaction database that comprehensively describes the behaviour of the vertex. A typical example is the social network, where the behaviour of every user is depicted by a transaction database that stores his daily posted contents. A transaction database is a set of transactions, where a transaction is a set of items. Every path of the network is a sequence of vertices that induces multiple sequences of transactions. The sequences of transactions induced by all of the paths in the network forms an extremely large sequence database. Finding frequent sequential patterns from such sequence database discovers interesting subsequences that frequently appear in many paths of the network. However, it is a challenging task, since the sequence database induced by a database graph is too large to be explicitly induced and stored. In this paper, we propose the novel notion of database graph, which naturally models a wide spectrum of real world networks by associating each vertex with a transaction database. Our goal is to find the top-k frequent sequential patterns in the sequence database induced from a database graph. We prove that this problem is #P-hard. To tackle this problem, we propose an efficient two-step sampling algorithm that approximates the top-k frequent sequential patterns with provable quality guarantee. Extensive experimental results on synthetic and real-world data sets demonstrate the effectiveness and efficiency of our method.

cs.DB↗

arXiv2018

Tracking Top-K Influential Vertices in Dynamic Networks

Influence propagation in networks has enjoyed fruitful applications and has been extensively studied in literature. However, only very limited preliminary studies tackled the challenges in handling highly dynamic changes in real networks. In this paper, we tackle the problem of tracking top-$k$ influential vertices in dynamic networks, where the dynamic changes are modeled as a stream of edge weight updates. Under the popularly adopted linear threshold (LT) model and the independent cascade (IC) model, we address two essential versions of the problem: tracking the top-$k$ influential individuals and finding the best $k$-seed set to maximize the influence spread (Influence Maximization). We adopt the polling-based method and maintain a sample of random RR sets so that we can approximate the influence of vertices with provable quality guarantees. It is known that updating RR sets over dynamic changes of a network can be easily done by a reservoir sampling method, so the key challenge is to efficiently decide how many RR sets are needed to achieve good quality guarantees. We use two simple signals, which both can be accessed in $O(1)$ time, to decide a proper number of RR sets. We prove the effectiveness of our methods. For both tasks the error incurred in our method is only a multiplicative factor to the ground truth. For influence maximization, we also propose an efficient query algorithm for finding the $k$ seeds, which is one order of magnitude faster than the state-of-the-art query algorithm in practice. In addition to the thorough theoretical results, our experimental results on large real networks clearly demonstrate the effectiveness and efficiency of our algorithms.

cs.SI↗

arXiv2018

Mining Density Contrast Subgraphs

Dense subgraph discovery is a key primitive in many graph mining applications, such as detecting communities in social networks and mining gene correlation from biological data. Most studies on dense subgraph mining only deal with one graph. However, in many applications, we have more than one graph describing relations among a same group of entities. In this paper, given two graphs sharing the same set of vertices, we investigate the problem of detecting subgraphs that contrast the most with respect to density. We call such subgraphs Density Contrast Subgraphs, or DCS in short. Two widely used graph density measures, average degree and graph affinity, are considered. For both density measures, mining DCS is equivalent to mining the densest subgraph from a "difference" graph, which may have both positive and negative edge weights. Due to the existence of negative edge weights, existing dense subgraph detection algorithms cannot identify the subgraph we need. We prove the computational hardness of mining DCS under the two graph density measures and develop efficient algorithms to find DCS. We also conduct extensive experiments on several real-world datasets to evaluate our algorithms. The experimental results show that our algorithms are both effective and efficient.

cs.SI↗

arXiv2017

Tracking Influential Nodes in Dynamic Networks

In this paper, we tackle a challenging problem inherent in a series of applications: tracking the influential nodes in dynamic networks. Specifically, we model a dynamic network as a stream of edge weight updates. This general model embraces many practical scenarios as special cases, such as edge and node insertions, deletions as well as evolving weighted graphs. Under the popularly adopted linear threshold model and independent cascade model, we consider two essential versions of the problem: finding the nodes whose influences passing a user specified threshold and finding the top-$k$ most influential nodes. Our key idea is to use the polling-based methods and maintain a sample of random RR sets so that we can approximate the influence of nodes with provable quality guarantees. We develop an efficient algorithm that incrementally updates the sample random RR sets against network changes. We also design methods to determine the proper sample sizes for the two versions of the problem so that we can provide strong quality guarantees and, at the same time, be efficient in both space and time. In addition to the thorough theoretical results, our experimental results on $5$ real network data sets clearly demonstrate the effectiveness and efficiency of our algorithms.

cs.SI↗

arXiv2016

Activity Maximization by Effective Information Diffusion in Social Networks

In a social network, even about the same information the excitements between different pairs of users are different. If you want to spread a piece of new information and maximize the expected total amount of excitements, which seed users should you choose? This problem indeed is substantially different from the renowned influence maximization problem and cannot be tackled using the existing approaches. In this paper, motivated by the demand in a few interesting applications, we model the novel problem of activity maximization. We tackle the problem systematically. We first analyze the complexity and the approximability of the problem. We develop an upper bound and a lower bound that are submodular so that the Sandwich framework can be applied. We then devise a polling-based randomized algorithm that guarantees a data dependent approximation factor. Our experiments on three real data sets clearly verify the effectiveness and scalability of our method, as well as the advantage of our method against the other heuristic methods.

cs.SI↗

arXiv2015

Information Coverage Maximization in Social Networks

Social networks, due to their popularity, have been studied extensively these years. A rich body of these studies is related to influence maximization, which aims to select a set of seed nodes for maximizing the expected number of active nodes at the end of the process. However, the set of active nodes can not fully represent the true coverage of information propagation. A node may be informed of the information when any of its neighbours become active and try to activate it, though this node (namely informed node) is still inactive. Therefore, we need to consider both active nodes and informed nodes that are aware of the information when we study the coverage of information propagation in a network. Along this line, in this paper we propose a new problem called Information Coverage Maximization that aims to maximize the expected number of both active nodes and informed ones. After we prove that this problem is NP-hard and submodular in the independent cascade model and the linear threshold model, we design two algorithms to solve it. Extensive experiments on three real-world data sets demonstrate the performance of the proposed algorithms.

cs.SI↗