arXiv subjects

Raymond Chi-Wing Wong

Publications and source records attributed to Raymond Chi-Wing Wong.

At least 37 records · Page 2Linked to original sources

arXiv2024

Towards Robustness of Text-to-Visualization Translation against Lexical and Phrasal Variability

Text-to-Vis is an emerging task in the natural language processing (NLP) area that aims to automatically generate data visualizations from natural language questions (NLQs). Despite their progress, existing text-to-vis models often heavily rely on lexical matching between words in the questions and tokens in data schemas. This overreliance on lexical matching may lead to a diminished level of model robustness against input variations. In this study, we thoroughly examine the robustness of current text-to-vis models, an area that has not previously been explored. In particular, we construct the first robustness dataset nvBench-Rob, which contains diverse lexical and phrasal variations based on the original text-to-vis benchmark nvBench. Then, we found that the performance of existing text-to-vis models on this new dataset dramatically drops, implying that these methods exhibit inadequate robustness overall. Finally, we propose a novel framework based on Retrieval-Augmented Generation (RAG) technique, named GRED, specifically designed to address input perturbations in these two variants. The framework consists of three parts: NLQ-Retrieval Generator, Visualization Query-Retrieval Retuner and Annotation-based Debugger, which are used to tackle the challenges posed by natural language variants, programming style differences and data schema variants, respectively. Extensive experimental evaluations show that, compared to the state-of-the-art model RGVisNet in the Text-to-Vis field, GRED performs better in terms of model robustness, with a 32% increase in accuracy on the proposed nvBench-Rob dataset.

cs.CL↗

arXiv2023

Automatic Data Visualization Generation from Chinese Natural Language Questions

Data visualization has emerged as an effective tool for getting insights from massive datasets. Due to the hardness of manipulating the programming languages of data visualization, automatic data visualization generation from natural languages (Text-to-Vis) is becoming increasingly popular. Despite the plethora of research effort on the English Text-to-Vis, studies have yet to be conducted on data visualization generation from questions in Chinese. Motivated by this, we propose a Chinese Text-to-Vis dataset in the paper and demonstrate our first attempt to tackle this problem. Our model integrates multilingual BERT as the encoder, boosts the cross-lingual ability, and infuses the $n$-gram information into our word representation learning. Our experimental results show that our dataset is challenging and deserves further research.

cs.CL↗

arXiv2023

Marrying Dialogue Systems with Data Visualization: Interactive Data Visualization Generation from Natural Language Conversations

Data visualization (DV) has become the prevailing tool in the market due to its effectiveness into illustrating insights in vast amounts of data. To lower the barrier of using DVs, automatic DV tasks, such as natural language question (NLQ) to visualization translation (formally called text-to-vis), have been investigated in the research community. However, text-to-vis assumes the NLQ to be well-organized and expressed in a single sentence. However, in real-world settings, complex DV is needed through consecutive exchanges between the DV system and the users. In this paper, we propose a new task named CoVis, short for Conversational text-to-Visualization, aiming at constructing DVs through a series of interactions between users and the system. Since it is the task which has not been studied in the literature, we first build a benchmark dataset named Dial-NVBench, including dialogue sessions with a sequence of queries from a user and responses from the system. Then, we propose a multi-modal neural network named MMCoVisNet to answer these DV-related queries. In particular, MMCoVisNet first fully understands the dialogue context and determines the corresponding responses. Then, it uses adaptive decoders to provide the appropriate replies: (i) a straightforward text decoder is used to produce general responses, (ii) an SQL-form decoder is applied to synthesize data querying responses, and (iii) a DV-form decoder tries to construct the appropriate DVs. We comparatively evaluate MMCoVisNet with other baselines over our proposed benchmark dataset. Experimental results validate that MMCoVisNet performs better than existing baselines and achieves a state-of-the-art performance.

cs.AI↗

arXiv2022

Fake News Detection with Heterogeneous Transformer

The dissemination of fake news on social networks has drawn public need for effective and efficient fake news detection methods. Generally, fake news on social networks is multi-modal and has various connections with other entities such as users and posts. The heterogeneity in both news content and the relationship with other entities in social networks brings challenges to designing a model that comprehensively captures the local multi-modal semantics of entities in social networks and the global structural representation of the propagation patterns, so as to classify fake news effectively and accurately. In this paper, we propose a novel Transformer-based model: HetTransformer to solve the fake news detection problem on social networks, which utilises the encoder-decoder structure of Transformer to capture the structural information of news propagation patterns. We first capture the local heterogeneous semantics of news, post, and user entities in social networks. Then, we apply Transformer to capture the global structural representation of the propagation patterns in social networks for fake news detection. Experiments on three real-world datasets demonstrate that our model is able to outperform the state-of-the-art baselines in fake news detection.

cs.SI↗

arXiv2022

Approximating Regret Minimizing Sets: A Happiness Perspective

A Regret Minimizing Set (RMS) is a useful concept in which a smaller subset of a database is selected while mostly preserving the best scores along every possible utility function. In this paper, we study the $k$-Regret Minimizing Sets ($k$-RMS) and Average Regret Minimizing Sets (ARMS) problems. $k$-RMS selects $r$ records from a database such that the maximum regret ratio between the $k$-th best score in the database and the best score in the selected records for any possible utility function is minimized. Meanwhile, ARMS minimizes the average of this ratio within a distribution of utility functions. Particularly, we study approximation algorithms for $k$-RMS and ARMS from the perspective of approximating the happiness ratio, which is equivalent to one minus the regret ratio. In this paper, we show that the problem of approximating the happiness of a $k$-RMS within any finite factor is NP-Hard when the dimensionality of the database is unconstrained and extend the result to an inapproximability proof for the regret. We then provide approximation algorithms for approximating the happiness of ARMS with better approximation ratios and time complexities than known algorithms for approximating the regret. We further provide dataset reduction schemes which can be used to reduce the runtime of existing heuristic based algorithms, as well as to derive polynomial-time approximation schemes for $k$-RMS when dimensionality is fixed. Finally, we provide experimental validation.

cs.DB↗

arXiv2022

Speech-to-SQL: Towards Speech-driven SQL Query Generation From Natural Language Question

Speech-based inputs have been gaining significant momentum with the popularity of smartphones and tablets in our daily lives, since voice is the most easiest and efficient way for human-computer interaction. This paper works towards designing more effective speech-based interfaces to query the structured data in relational databases. We first identify a new task named Speech-to-SQL, which aims to understand the information conveyed by human speech and directly translate it into structured query language (SQL) statements. A naive solution to this problem can work in a cascaded manner, that is, an automatic speech recognition (ASR) component followed by a text-to-SQL component. However, it requires a high-quality ASR system and also suffers from the error compounding problem between the two components, resulting in limited performance. To handle these challenges, we further propose a novel end-to-end neural architecture named SpeechSQLNet to directly translate human speech into SQL queries without an external ASR step. SpeechSQLNet has the advantage of making full use of the rich linguistic information presented in speech. To the best of our knowledge, this is the first attempt to directly synthesize SQL based on arbitrary natural language questions, rather than a natural language-based version of SQL or its variants with a limited SQL grammar. To validate the effectiveness of the proposed problem and model, we further construct a dataset named SpeechQL, by piggybacking the widely-used text-to-SQL datasets. Extensive experimental evaluations on this dataset show that SpeechSQLNet can directly synthesize high-quality SQL queries from human speech, outperforming various competitive counterparts as well as the cascaded methods in terms of exact match accuracies.

cs.DB↗

arXiv2020

A Fully Dynamic Algorithm for k-Regret Minimizing Sets

Selecting a small set of representatives from a large database is important in many applications such as multi-criteria decision making, web search, and recommendation. The $k$-regret minimizing set ($k$-RMS) problem was recently proposed for representative tuple discovery. Specifically, for a large database $P$ of tuples with multiple numerical attributes, the $k$-RMS problem returns a size-$r$ subset $Q$ of $P$ such that, for any possible ranking function, the score of the top-ranked tuple in $Q$ is not much worse than the score of the $k$\textsuperscript{th}-ranked tuple in $P$. Although the $k$-RMS problem has been extensively studied in the literature, existing methods are designed for the static setting and cannot maintain the result efficiently when the database is updated. To address this issue, we propose the first fully-dynamic algorithm for the $k$-RMS problem that can efficiently provide the up-to-date result w.r.t.~any insertion and deletion in the database with a provable guarantee. Experimental results on several real-world and synthetic datasets demonstrate that our algorithm runs up to four orders of magnitude faster than existing $k$-RMS algorithms while returning results of nearly equal quality.

cs.DB↗

arXiv2020

Bridging the Gap Between Theory and Practice on Insertion-Intensive Database

With the prevalence of online platforms, today, data is being generated and accessed by users at a very high rate. Besides, applications such as stock trading or high frequency trading require guaranteed low delays for performing an operation on a database. It is consequential to design databases that guarantee data insertion and query at a consistently high rate without introducing any long delay during insertion. In this paper, we propose Nested B-trees (NB-trees), an index that can achieve a consistently high insertion rate on large volumes of data, while providing asymptotically optimal query performance that is very efficient in practice. Nested B-trees support insertions at rates higher than LSM-trees, the state-of-the-art index for insertion-intensive workloads, while avoiding their long insertion delays and improving on their query performance. They approach the query performance of B-trees when complemented with Bloom filters. In our experiments, NB-trees had worst-case delays up to 1000 smaller than LevelDB, RocksDB and bLSM, commonly used LSM-tree data-stores, could perform queries more than 4 times faster than LevelDB and 1.5 times faster than bLSM and RocksDB, while also outperforming them in terms of average insertion rate.

cs.DB↗

arXiv2019

L2RS: A Learning-to-Rescore Mechanism for Automatic Speech Recognition

Modern Automatic Speech Recognition (ASR) systems primarily rely on scores from an Acoustic Model (AM) and a Language Model (LM) to rescore the N-best lists. With the abundance of recent natural language processing advances, the information utilized by current ASR for evaluating the linguistic and semantic legitimacy of the N-best hypotheses is rather limited. In this paper, we propose a novel Learning-to-Rescore (L2RS) mechanism, which is specialized for utilizing a wide range of textual information from the state-of-the-art NLP models and automatically deciding their weights to rescore the N-best lists for ASR systems. Specifically, we incorporate features including BERT sentence embedding, topic vector, and perplexity scores produced by n-gram LM, topic modeling LM, BERT LM and RNNLM to train a rescoring model. We conduct extensive experiments based on a public dataset, and experimental results show that L2RS outperforms not only traditional rescoring methods but also its deep neural network counterparts by a substantial improvement of 20.67% in terms of NDCG@10. L2RS paves the way for developing more effective rescoring models for ASR.

cs.CL↗

arXiv2019

Big Data Analytics for Large Scale Wireless Networks: Challenges and Opportunities

The wide proliferation of various wireless communication systems and wireless devices has led to the arrival of big data era in large scale wireless networks. Big data of large scale wireless networks has the key features of wide variety, high volume, real-time velocity and huge value leading to the unique research challenges that are different from existing computing systems. In this paper, we present a survey of the state-of-art big data analytics (BDA) approaches for large scale wireless networks. In particular, we categorize the life cycle of BDA into four consecutive stages: Data Acquisition, Data Preprocessing, Data Storage and Data Analytics. We then present a detailed survey of the technical solutions to the challenges in BDA for large scale wireless networks according to each stage in the life cycle of BDA. Moreover, we discuss the open research issues and outline the future directions in this promising area.

cs.NI↗

arXiv2016

On Capacity and Delay of Multi-channel Wireless Networks with Infrastructure Support

In this paper, we propose a novel multi-channel network with infrastructure support, called an MC-IS network, which has not been studied in the literature. To the best of our knowledge, we are the first to study such an MC-IS network. Our proposed MC-IS network has a number of advantages over three existing conventional networks, namely a single-channel wireless ad hoc network (called an SC-AH network), a multi-channel wireless ad hoc network (called an MC-AH network) and a single-channel network with infrastructure support (called an SC-IS network). In particular, the network capacity of our proposed MC-IS network is $\sqrt{n \log n}$ times higher than that of an SC-AH network and an MC-AH network and the same as that of an SC-IS network, where $n$ is the number of nodes in the network. The average delay of our MC-IS network is $\sqrt{\log n/n}$ times lower than that of an SC-AH network and an MC-AH network, and $\min\{C_I,m\}$ times lower than the average delay of an SC-IS network, where $C_I$ and $m$ denote the number of channels dedicated for infrastructure communications and the number of interfaces mounted at each infrastructure node, respectively. Our analysis on an MC-IS network equipped with omni-directional antennas only has been extended to an MC-IS network equipped with directional antennas only, which are named as an MC-IS-DA network. We show that an MC-IS-DA network has an even lower delay of $\frac{c}{\lfloor \frac{2π}θ\rfloor \cdot C_I}$ compared with an SC-IS network and our MC-IS network. For example, when $C_I=12$ and $θ=\fracπ{12}$, an MC-IS-DA network can further reduce the delay by 24 times lower that of an MC-IS network and reduce the delay by 288 times lower than that of an SC-IS network.

cs.NI↗

arXiv2014

Hop Doubling Label Indexing for Point-to-Point Distance Querying on Scale-Free Networks

We study the problem of point-to-point distance querying for massive scale-free graphs, which is important for numerous applications. Given a directed or undirected graph, we propose to build an index for answering such queries based on a hop-doubling labeling technique. We derive bounds on the index size, the computation costs and I/O costs based on the properties of unweighted scale-free graphs. We show that our method is much more efficient compared to the state-of-the-art technique, in terms of both querying time and indexing time. Our empirical study shows that our method can handle graphs that are orders of magnitude larger than existing methods.

cs.DB↗

arXiv2014

Multi-channel Wireless Networks with Infrastructure Support: Capacity and Delay

In this paper, we propose a novel multi-channel network with infrastructure support, called an \textit{MC-IS} network, which has not been studied in the literature. To the best of our knowledge, we are the first to study such an \textit{MC-IS} network. Our \textit{MC-IS} network is equipped with a number of infrastructure nodes which can communicate with common nodes using a number of channels where a communication between a common node and an infrastructure node is called an infrastructure communication and a communication between two common nodes is called an ad-hoc communication. Our proposed \textit{MC-IS} network has a number of advantages over three existing conventional networks, namely a single-channel wireless ad hoc network (called an \textit{SC-AH} network), a multi-channel wireless ad hoc network (called an \textit{MC-AH} network) and a single-channel network with infrastructure support (called an \textit{SC-IS} network). In particular, the \textit{network capacity} of our proposed \textit{MC-IS} network is $\sqrt{n \log n}$ times higher than that of an \textit{SC-AH} network and an \textit{MC-AH} network and the same as that of an \textit{SC-IS} network, where $n$ is the number of nodes in the network. The \textit{average delay} of our \textit{MC-IS} network is $\sqrt{\log n/n}$ times lower than that of an \textit{SC-AH} network and an \textit{MC-AH} network, and $\min(C_I,m)$ times lower than the average delay of an \textit{SC-IS} network, where $C_I$ and $m$ denote the number of channels dedicated for infrastructure communications and the number of interfaces mounted at each infrastructure node, respectively.

cs.NI↗

arXiv2012

IS-LABEL: an Independent-Set based Labeling Scheme for Point-to-Point Distance Querying on Large Graphs

We study the problem of computing shortest path or distance between two query vertices in a graph, which has numerous important applications. Quite a number of indexes have been proposed to answer such distance queries. However, all of these indexes can only process graphs of size barely up to 1 million vertices, which is rather small in view of many of the fast-growing real-world graphs today such as social networks and Web graphs. We propose an efficient index, which is a novel labeling scheme based on the independent set of a graph. We show that our method can handle graphs of size three orders of magnitude larger than those existing indexes.

cs.DB↗

arXiv2012

Small Count Privacy and Large Count Utility in Data Publishing

While the introduction of differential privacy has been a major breakthrough in the study of privacy preserving data publication, some recent work has pointed out a number of cases where it is not possible to limit inference about individuals. The dilemma that is intrinsic in the problem is the simultaneous requirement of data utility in the published data. Differential privacy does not aim to protect information about an individual that can be uncovered even without the participation of the individual. However, this lack of coverage may violate the principle of individual privacy. Here we propose a solution by providing protection to sensitive information, by which we refer to the answers for aggregate queries with small counts. Previous works based on $\ell$-diversity can be seen as providing a special form of this kind of protection. Our method is developed with another goal which is to provide differential privacy guarantee, and for that we introduce a more refined form of differential privacy to deal with certain practical issues. Our empirical studies show that our method can preserve better utilities than a number of state-of-the-art methods although these methods do not provide the protections that we provide.

cs.DB↗

arXiv2009

Anonymization with Worst-Case Distribution-Based Background Knowledge

Background knowledge is an important factor in privacy preserving data publishing. Distribution-based background knowledge is one of the well studied background knowledge. However, to the best of our knowledge, there is no existing work considering the distribution-based background knowledge in the worst case scenario, by which we mean that the adversary has accurate knowledge about the distribution of sensitive values according to some tuple attributes. Considering this worst case scenario is essential because we cannot overlook any breaching possibility. In this paper, we propose an algorithm to anonymize dataset in order to protect individual privacy by considering this background knowledge. We prove that the anonymized datasets generated by our proposed algorithm protects individual privacy. Our empirical studies show that our method preserves high utility for the published data at the same time.

cs.DB↗

arXiv2009

Can the Utility of Anonymized Data be used for Privacy Breaches?

Group based anonymization is the most widely studied approach for privacy preserving data publishing. This includes k-anonymity, l-diversity, and t-closeness, to name a few. The goal of this paper is to raise a fundamental issue on the privacy exposure of the current group based approach. This has been overlooked in the past. The group based anonymization approach basically hides each individual record behind a group to preserve data privacy. If not properly anonymized, patterns can actually be derived from the published data and be used by the adversary to breach individual privacy. For example, from the medical records released, if patterns such as people from certain countries rarely suffer from some disease can be derived, then the information can be used to imply linkage of other people in an anonymized group with this disease with higher likelihood. We call the derived patterns from the published data the foreground knowledge. This is in contrast to the background knowledge that the adversary may obtain from other channels as studied in some previous work. Finally, we show by experiments that the attack is realistic in the privacy benchmark dataset under the traditional group based anonymization approach.

cs.DB↗

arXiv2009

Preserving Individual Privacy in Serial Data Publishing

While previous works on privacy-preserving serial data publishing consider the scenario where sensitive values may persist over multiple data releases, we find that no previous work has sufficient protection provided for sensitive values that can change over time, which should be the more common case. In this work we propose to study the privacy guarantee for such transient sensitive values, which we call the global guarantee. We formally define the problem for achieving this guarantee and derive some theoretical properties for this problem. We show that the anonymized group sizes used in the data anonymization is a key factor in protecting individual privacy in serial publication. We propose two strategies for anonymization targeting at minimizing the average group size and the maximum group size. Finally, we conduct experiments on a medical dataset to show that our method is highly efficient and also produces published data of very high utility.

cs.DB↗