arXiv subjects

Dongmei Zhang

Publications and source records attributed to Dongmei Zhang.

233 records · Page 13Linked to original sources

arXiv2019

A Hybrid Semantic Parsing Approach for Tabular Data Analysis

This paper presents a novel approach to translating natural language questions to SQL queries for given tables, which meets three requirements as a real-world data analysis application: cross-domain, multilingualism and enabling quick-start. Our proposed approach consists of: (1) a novel data abstraction step before the parser to make parsing table-agnosticism; (2) a set of semantic rules for parsing abstracted data-analysis questions to intermediate logic forms as tree derivations to reduce the search space; (3) a neural-based model as a local scoring function on a span-based semantic parser for structured optimization and efficient inference. Experiments show that our approach outperforms state-of-the-art algorithms on a large open benchmark dataset WikiSQL. We also achieve promising results on a small dataset for more complex queries in both English and Chinese, which demonstrates our language expansion and quick-start ability.

cs.AI↗

arXiv2019

A Split-and-Recombine Approach for Follow-up Query Analysis

Context-dependent semantic parsing has proven to be an important yet challenging task. To leverage the advances in context-independent semantic parsing, we propose to perform follow-up query analysis, aiming to restate context-dependent natural language queries with contextual information. To accomplish the task, we propose STAR, a novel approach with a well-designed two-phase process. It is parser-independent and able to handle multifarious follow-up scenarios in different domains. Experiments on the FollowUp dataset show that STAR outperforms the state-of-the-art baseline by a large margin of nearly 8%. The superiority on parsing results verifies the feasibility of follow-up query analysis. We also explore the extensibility of STAR on the SQA dataset, which is very promising.

cs.CL↗

arXiv2019

Text-to-Viz: Automatic Generation of Infographics from Proportion-Related Natural Language Statements

Combining data content with visual embellishments, infographics can effectively deliver messages in an engaging and memorable manner. Various authoring tools have been proposed to facilitate the creation of infographics. However, creating a professional infographic with these authoring tools is still not an easy task, requiring much time and design expertise. Therefore, these tools are generally not attractive to casual users, who are either unwilling to take time to learn the tools or lacking in proper design expertise to create a professional infographic. In this paper, we explore an alternative approach: to automatically generate infographics from natural language statements. We first conducted a preliminary study to explore the design space of infographics. Based on the preliminary study, we built a proof-of-concept system that automatically converts statements about simple proportion-related statistics to a set of infographics with pre-designed styles. Finally, we demonstrated the usability and usefulness of the system through sample results, exhibits, and expert reviews.

cs.HC↗

arXiv2019

Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation

We present a neural approach called IRNet for complex and cross-domain Text-to-SQL. IRNet aims to address two challenges: 1) the mismatch between intents expressed in natural language (NL) and the implementation details in SQL; 2) the challenge in predicting columns caused by the large number of out-of-domain words. Instead of end-to-end synthesizing a SQL query, IRNet decomposes the synthesis process into three phases. In the first phase, IRNet performs a schema linking over a question and a database schema. Then, IRNet adopts a grammar-based neural model to synthesize a SemQL query which is an intermediate representation that we design to bridge NL and SQL. Finally, IRNet deterministically infers a SQL query from the synthesized SemQL query with domain knowledge. On the challenging Text-to-SQL benchmark Spider, IRNet achieves 46.7% accuracy, obtaining 19.5% absolute improvement over previous state-of-the-art approaches. At the time of writing, IRNet achieves the first position on the Spider leaderboard.

cs.CL↗

arXiv2019

FANDA: A Novel Approach to Perform Follow-up Query Analysis

Recent work on Natural Language Interfaces to Databases (NLIDB) has attracted considerable attention. NLIDB allow users to search databases using natural language instead of SQL-like query languages. While saving the users from having to learn query languages, multi-turn interaction with NLIDB usually involves multiple queries where contextual information is vital to understand the users' query intents. In this paper, we address a typical contextual understanding problem, termed as follow-up query analysis. In spite of its ubiquity, follow-up query analysis has not been well studied due to two primary obstacles: the multifarious nature of follow-up query scenarios and the lack of high-quality datasets. Our work summarizes typical follow-up query scenarios and provides a new FollowUp dataset with $1000$ query triples on 120 tables. Moreover, we propose a novel approach FANDA, which takes into account the structures of queries and employs a ranking model with weakly supervised max-margin learning. The experimental results on FollowUp demonstrate the superiority of FANDA over multiple baselines across multiple metrics.

cs.CL↗

arXiv2018

QuanFuzz: Fuzz Testing of Quantum Program

Nowadays, quantum program is widely used and quickly developed. However, the absence of testing methodology restricts their quality. Different input format and operator from traditional program make this issue hard to resolve. In this paper, we present QuanFuzz, a search-based test input generator for quantum program. We define the quantum sensitive information to evaluate test input for quantum program and use matrix generator to generate test cases with higher coverage. First, we extract quantum sensitive information -- measurement operations on those quantum registers and the sensitive branches associated with those measurement results, from the quantum source code. Then, we use the sensitive information guided algorithm to mutate the initial input matrix and select those matrices which improve the probability weight for a value of the quantum register to trigger the sensitive branch. The process keeps iterating until the sensitive branch triggered. We tested QuanFuzz on benchmarks and acquired 20% - 60% more coverage compared to traditional testing input generation.

cs.SE↗

arXiv2017

Automated Refactoring of Nested-IF Formulae in Spreadsheets

Spreadsheets are the most popular end-user programming software, where formulae act like programs and also have smells. One well recognized common smell of spreadsheet formulae is nest-IF expressions, which have low readability and high cognitive cost for users, and are error-prone during reuse or maintenance. However, end users usually lack essential programming language knowledge and skills to tackle or even realize the problem. The previous research work has made very initial attempts in this aspect, while no effective and automated approach is currently available. This paper firstly proposes an AST-based automated approach to systematically refactoring nest-IF formulae. The general idea is two-fold. First, we detect and remove logic redundancy on the AST. Second, we identify higher-level semantics that have been fragmented and scattered, and reassemble the syntax using concise built-in functions. A comprehensive evaluation has been conducted against a real-world spreadsheet corpus, which is collected in a leading IT company for research purpose. The results with over 68,000 spreadsheets with 27 million nest-IF formulae reveal that our approach is able to relieve the smell of over 99\% of nest-IF formulae. Over 50% of the refactorings have reduced nesting levels of the nest-IFs by more than a half. In addition, a survey involving 49 participants indicates that for most cases the participants prefer the refactored formulae, and agree on that such automated refactoring approach is necessary and helpful.

cs.SE↗

arXiv2017

Deep API Learning

Developers often wonder how to implement a certain functionality (e.g., how to parse XML files) using APIs. Obtaining an API usage sequence based on an API-related natural language query is very helpful in this regard. Given a query, existing approaches utilize information retrieval models to search for matching API sequences. These approaches treat queries and APIs as bag-of-words (i.e., keyword matching or word-to-word alignment) and lack a deep understanding of the semantics of the query. We propose DeepAPI, a deep learning based approach to generate API usage sequences for a given natural language query. Instead of a bags-of-words assumption, it learns the sequence of words in a query and the sequence of associated APIs. DeepAPI adapts a neural language model named RNN Encoder-Decoder. It encodes a word sequence (user query) into a fixed-length context vector, and generates an API sequence based on the context vector. We also augment the RNN Encoder-Decoder by considering the importance of individual APIs. We empirically evaluate our approach with more than 7 million annotated code snippets collected from GitHub. The results show that our approach generates largely accurate API sequences and outperforms the related approaches.

cs.SE↗

arXiv2017

DeepAM: Migrate APIs with Multi-modal Sequence to Sequence Learning

Computer programs written in one language are often required to be ported to other languages to support multiple devices and environments. When programs use language specific APIs (Application Programming Interfaces), it is very challenging to migrate these APIs to the corresponding APIs written in other languages. Existing approaches mine API mappings from projects that have corresponding versions in two languages. They rely on the sparse availability of bilingual projects, thus producing a limited number of API mappings. In this paper, we propose an intelligent system called DeepAM for automatically mining API mappings from a large-scale code corpus without bilingual projects. The key component of DeepAM is based on the multimodal sequence to sequence learning architecture that aims to learn joint semantic representations of bilingual API sequences from big source code data. Experimental results indicate that DeepAM significantly increases the accuracy of API mappings as well as the number of API mappings, when compared with the state-of-the-art approaches.

cs.SE↗

arXiv2015

Hardware Impairments Aware Transceiver for Full-Duplex Massive MIMO Relaying

This paper studies the massive MIMO full-duplex relaying (MM-FDR), where multiple source-destination pairs communicate simultaneously with the help of a common full-duplex relay equipped with very large antenna arrays. Different from the traditional MM-FDR protocol, a general model where sources/destinations are allowed to equip with multiple antennas is considered. In contrast to the conventional MIMO system, massive MIMO must be built with low-cost components which are prone to hardware impairments. In this paper, the effect of hardware impairments is taken into consideration, and is modeled using transmit/receive distortion noises. We propose a low complexity hardware impairments aware transceiver scheme (named as HIA scheme) to mitigate the distortion noises by exploiting the statistical knowledge of channels and antenna arrays at sources and destinations. A joint degree of freedom and power optimization algorithm is presented to further optimize the spectral efficiency of HIA based MM-FDR. The results show that the HIA scheme can mitigate the "ceiling effect" appears in traditional MM-FDR protocol, if the numbers of antennas at sources and destinations can scale with that at the relay.

cs.IT↗

arXiv2014

Max-SINR Receiver for HMCT Systems over Non-Stationary Doubly Dispersive Channel

In this paper, a maximizing Signal-to-Interference plus-Noise Ratio (Max-SINR) receiver for Hexagonal Multicarrier Transmission (HMCT) system over non-stationary doubly dispersive (NSDD) channel is proposed. The closed-form timing offset expression of the prototype pulse for the proposed Max-SINR HMCT receiver over NSDD channel is derived. Simulation results show that the proposed Max-SINR receiver outperforms traditional projection scheme and obtains an approximation to the theoretical upper bound SINR performance within all the local stationarity regions (LSRs). Meanwhile, the SINR performance of the proposed Max-SINR HMCT receiver is robust to the estimation error between the estimated value and the real value of root mean square (RMS) delay spread.

cs.IT↗

arXiv2014

Performance Analysis of Interference-Limited Three-Phase Two-Way Relaying with Direct Channel

This paper investigates the performance of interference-limited three-phase two-way relaying with direct channel between two terminals in Rayleigh fading channels. The outage probability, sum bit error rate (BER) and ergodic sum rate are analyzed for a general model that both terminals and relay are corrupted by co-channel interference. We first derive the closed-form expressions of cumulative distribution function (CDF) for received signal-to-interference-plus-noise ratio (SINR) at the terminal. Based on the results for CDF, the lower bounds, approximate expressions as well as the asymptotic expressions for outage probability and sum BER are derived in closed-form with different computational complexities and accuracies. The approximate expression for ergodic sum rate is also presented. With the theoretic results, we consider the optimal power allocation at the relay and optimal relay location problems that aiming to minimize the outage and sum BER performances of the protocol. It is shown that jointly optimization of power and relay location can provide the best performance. Simulation results are presented to study the effect of system parameters while verify the theoretic analysis. The results show that three-phase TWR protocol can outperform two-phase TWR protocol in ergodic sum rate when the interference power at the relay is much larger than that at the terminals. This is in sharp contrast with the conclusion in interference free scenario. Moreover, we show that an estimation error on the interference channel will not affect the system performance significantly, while a very small estimation error on the desired channels can degrade the performance considerably.

cs.IT↗

arXiv2013

Joint Physical Network Coding and LDPC decoding for Two Way Wireless Relaying

In this paper, we investigate the joint design of channel and network coding in bi-directional relaying systems and propose a combined low complexity physical network coding and LDPC decoding scheme. For the same LDPC codes employed at both source nodes, we show that the relay can decodes the network coded codewords from the superimposed signal received from the BPSK-modulated multiple-access channel. Simulation results shown that this novel joint physical network coding and LDPC decoding method outperforms the existing MMSE network coding and LDPC decoding method over AWGN and complex MAC channel.

cs.IT↗

arXiv2013

On Max-SINR Receiver for Hexagonal Multicarrier Transmission Over Doubly Dispersive Channel

In this paper, a novel receiver for Hexagonal Multicarrier Transmission (HMT) system based on the maximizing Signal-to-Interference-plus-Noise Ratio (Max-SINR) criterion is proposed. Theoretical analysis shows that the prototype pulse of the proposed Max-SINR receiver should adapt to the root mean square (RMS) delay spread of the doubly dispersive (DD) channel with exponential power delay profile and U-shape Doppler spectrum. Simulation results show that the proposed Max-SINR receiver outperforms traditional projection scheme and obtains an approximation to the theoretical upper bound SINR performance within the full range of channel spread factor. Meanwhile, the SINR performance of the proposed prototype pulse is robust to the estimation error between the estimated value and the real value of time delay spread.

cs.IT↗

arXiv2013

Carrier Frequency Offset Estimation Approach for Multicarrier Transmission on Hexagonal Time-Frequency Lattice

In this paper, a novel carrier frequency offset estimation approach, including preamble structure, carrier frequency offset estimation algorithm, is proposed for hexagonal multi-carrier transmission (HMCT) system. The closed-form Cramer-Rao lower bound of the proposed carrier frequency offset estimation scheme is given. Theoretical analyses and simulation results show that the proposed preamble structure and carrier frequency offset estimation algorithm for HMCT system obtains an approximation to the Cramer-Rao lower bound mean square error (MSE) performance over the doubly dispersive (DD) propagation channel.

cs.IT↗

arXiv2013

On Max-SINR Receiver for HMT System over Doubly Dispersive Channel

In this paper, a novel receiver for Hexagonal Multicarrier Transmission (HMT) system based on the maximizing Signal-to-Interference-plus-Noise Ratio (Max-SINR) criterion is proposed. Theoretical analyses show that there is a timing offset between the prototype pulses of the proposed Max-SINR receiver and the traditional projection receiver. Meanwhile, the timing offset should be matched to the channel scattering factor of the doubly dispersive (DD) channel. The closed form timing offset expressions of the prototype pulse for Max-SINR HMT receiver over DD channel with different channel scattering functions are derived. Simulation results show that the proposed Max-SINR receiver outperforms traditional projection scheme and obtains an approximation to the theoretical upper bound SINR performance. Consistent with the SINR performance improvement, the bit error rate (BER) performance of HMT system has also been further improved by using the proposed Max-SINR receiver. Meanwhile, the SINR performance of the proposed Max-SINR receiver is robust to the channel delay spread estimation errors.

cs.IT↗

arXiv2012

Outage Performance of AF-based Time Division Broadcasting Protocol in the Presence of Co-channel Interference

In this paper, we investigate the outage performance of time division broadcasting (TDBC) protocol in independent but non-identical Rayleigh flat-fading channels, where all nodes are interfered by a finite number of co-channel interferers. We assume that the relay operates in the amplified-and-forward mode. A tight lower bound as well as the asymptotic expression of the outage probability is obtained in closed-form. Through both theoretic analyses and simulation results, we show that the achievable diversity of TDBC protocol is zero in the interference-limited scenario. Moreover, we study the impacts of interference power, number of interferers and relay placement on the outage probability. Finally, the correctness of our analytic results is validated via computer simulations.

cs.IT↗