arXiv subjects

Zhiguo Wang

Publications and source records attributed to Zhiguo Wang.

At least 55 records · Page 3Linked to original sources

arXiv2023

DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases

Question answering over knowledge bases (KBs) aims to answer natural language questions with factual information such as entities and relations in KBs. Previous methods either generate logical forms that can be executed over KBs to obtain final answers or predict answers directly. Empirical results show that the former often produces more accurate answers, but it suffers from non-execution issues due to potential syntactic and semantic errors in the generated logical forms. In this work, we propose a novel framework DecAF that jointly generates both logical forms and direct answers, and then combines the merits of them to get the final answers. Moreover, different from most of the previous methods, DecAF is based on simple free-text retrieval without relying on any entity linking tools -- this simplification eases its adaptation to different datasets. DecAF achieves new state-of-the-art accuracy on WebQSP, FreebaseQA, and GrailQA benchmarks, while getting competitive results on the ComplexWebQuestions benchmark.

cs.CL↗

arXiv2023

Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness

Neural text-to-SQL models have achieved remarkable performance in translating natural language questions into SQL queries. However, recent studies reveal that text-to-SQL models are vulnerable to task-specific perturbations. Previous curated robustness test sets usually focus on individual phenomena. In this paper, we propose a comprehensive robustness benchmark based on Spider, a cross-domain text-to-SQL benchmark, to diagnose the model robustness. We design 17 perturbations on databases, natural language questions, and SQL queries to measure the robustness from different angles. In order to collect more diversified natural question perturbations, we utilize large pretrained language models (PLMs) to simulate human behaviors in creating natural questions. We conduct a diagnostic study of the state-of-the-art models on the robustness set. Experimental results reveal that even the most robust model suffers from a 14.0% performance drop overall and a 50.7% performance drop on the most challenging perturbation. We also present a breakdown analysis regarding text-to-SQL model designs and provide insights for improving model robustness.

cs.CL↗

arXiv2023

Beyond ADMM: A Unified Client-variance-reduced Adaptive Federated Learning Framework

As a novel distributed learning paradigm, federated learning (FL) faces serious challenges in dealing with massive clients with heterogeneous data distribution and computation and communication resources. Various client-variance-reduction schemes and client sampling strategies have been respectively introduced to improve the robustness of FL. Among others, primal-dual algorithms such as the alternating direction of method multipliers (ADMM) have been found being resilient to data distribution and outperform most of the primal-only FL algorithms. However, the reason behind remains a mystery still. In this paper, we firstly reveal the fact that the federated ADMM is essentially a client-variance-reduced algorithm. While this explains the inherent robustness of federated ADMM, the vanilla version of it lacks the ability to be adaptive to the degree of client heterogeneity. Besides, the global model at the server under client sampling is biased which slows down the practical convergence. To go beyond ADMM, we propose a novel primal-dual FL algorithm, termed FedVRA, that allows one to adaptively control the variance-reduction level and biasness of the global model. In addition, FedVRA unifies several representative FL algorithms in the sense that they are either special instances of FedVRA or are close to it. Extensions of FedVRA to semi/un-supervised learning are also presented. Experiments based on (semi-)supervised image classification tasks demonstrate superiority of FedVRA over the existing schemes in learning scenarios with massive heterogeneous clients and client sampling.

cs.LG↗

arXiv2023

Flexo-photovoltaic effect and above-bandgap photovoltage in halide perovskites

Halide perovskites have outstanding photovoltaic properties which have been optimized through interfacial engineering. However, as these materials approach the limits imposed by the physics of semiconductor junctions, it is urgent to explore alternatives, such as the bulk photovoltaic effect, whose physical origin is different and not bound by the same limits. In this context, we focus on the flexo-photovoltaic effect, a type of bulk photovoltaic effect that was recently observed in oxides under strain gradients. We have measured the flexo-photovoltaic effect of MAPbBr3 and MAPbI3 crystals under bending and found it to be orders of magnitude larger than for SrTiO3, the benchmark flexo-photovoltaic oxide. For sufficiently large strain gradients, photovoltages bigger than the bandgap can be produced. Bulk photovoltaic effects are additive and, for MAPbI3, the flexo-photovoltage exists on top of a native bulk photovoltage that is hysteretic, consistent with the electrically switchable macroscopic polarization of this material. The results suggest that harnessing the flexo-photovoltaic effect through strain gradient engineering can provide a functional leap forward for halide perovskites.

cond-mat.mtrl-sci↗

arXiv2022

Importance of Synthesizing High-quality Data for Text-to-SQL Parsing

Recently, there has been increasing interest in synthesizing data to improve downstream text-to-SQL tasks. In this paper, we first examined the existing synthesized datasets and discovered that state-of-the-art text-to-SQL algorithms did not further improve on popular benchmarks when trained with augmented synthetic data. We observed two shortcomings: illogical synthetic SQL queries from independent column sampling and arbitrary table joins. To address these issues, we propose a novel synthesis framework that incorporates key relationships from schema, imposes strong typing, and conducts schema-distance-weighted column sampling. We also adopt an intermediate representation (IR) for the SQL-to-text task to further improve the quality of the generated natural language questions. When existing powerful semantic parsers are pre-finetuned on our high-quality synthesized data, our experiments show that these models have significant accuracy boosts on popular benchmarks, including new state-of-the-art performance on Spider.

cs.CL↗

arXiv2022

Nonlinear Set Membership Filter with State Estimation Constraints via Consensus-ADMM

This paper considers the state estimation problem for nonlinear dynamic systems with unknown but bounded noises. Set membership filter (SMF) is a popular algorithm to solve this problem. In the set membership setting, we investigate the filter problem where the state estimation requires to be constrained by a linear or nonlinear equality. We propose a consensus alternating direction method of multipliers (ADMM) based SMF algorithm for nonlinear dynamic systems. To deal with the difficulty of nonlinearity, instead of linearizing the nonlinear system, a semi-infinite programming (SIP) approach is used to transform the nonlinear system into a linear one, which allows us to obtain a more accurate estimation ellipsoid. For the solution of the SIP, an ADMM algorithm is proposed to handle the state estimation constraints, and each iteration of the algorithm can be solved efficiently. Finally, the proposed filter is applied to typical numerical examples to demonstrate its effectiveness.

math.OC↗

arXiv2022

Improving Text-to-SQL Semantic Parsing with Fine-grained Query Understanding

Most recent research on Text-to-SQL semantic parsing relies on either parser itself or simple heuristic based approach to understand natural language query (NLQ). When synthesizing a SQL query, there is no explicit semantic information of NLQ available to the parser which leads to undesirable generalization performance. In addition, without lexical-level fine-grained query understanding, linking between query and database can only rely on fuzzy string match which leads to suboptimal performance in real applications. In view of this, in this paper we present a general-purpose, modular neural semantic parsing framework that is based on token-level fine-grained query understanding. Our framework consists of three modules: named entity recognizer (NER), neural entity linker (NEL) and neural semantic parser (NSP). By jointly modeling query and database, NER model analyzes user intents and identifies entities in the query. NEL model links typed entities to schema and cell values in database. Parser model leverages available semantic information and linking results and synthesizes tree-structured SQL queries based on dynamically generated grammar. Experiments on SQUALL, a newly released semantic parsing dataset, show that we can achieve 56.8% execution accuracy on WikiTableQuestions (WTQ) test set, which outperforms the state-of-the-art model by 2.7%.

cs.CL↗

arXiv2022

REKnow: Enhanced Knowledge for Joint Entity and Relation Extraction

Relation extraction is an important but challenging task that aims to extract all hidden relational facts from the text. With the development of deep language models, relation extraction methods have achieved good performance on various benchmarks. However, we observe two shortcomings of previous methods: first, there is no unified framework that works well under various relation extraction settings; second, effectively utilizing external knowledge as background information is absent. In this work, we propose a knowledge-enhanced generative model to mitigate these two issues. Our generative model is a unified framework to sequentially generate relational triplets under various relation extraction settings and explicitly utilizes relevant knowledge from Knowledge Graph (KG) to resolve ambiguities. Our model achieves superior performance on multiple benchmarks and settings, including WebNLG, NYT10, and TACRED.

cs.CL↗

arXiv2022

Abnormal Phonon Angular Momentum due to Off-diagonal Elements in Density Matrix induced by Temperature Gradient

Nonzero mean value of phonon angular momentum (PAM) in chiral materials can be generated when a temperature gradient is applied. We find that both diagonal and off-diagonal terms of PAM contribute to mean PAM by using the Kubo formula where both diagonal and off-diagonal elements of the heat current operator are considered. The calculation results show that the off-diagonal term is dominant when the phonon scattering is strong enough. This finding reveals that the quantum transition between different phonon modes induced by temperature gradient strongly affects the local atomic rotation. Our discovery provides an explanation of the recently observed chiral phonon activated spin Seebeck effect.

cond-mat.mes-hall↗

arXiv2022

An Unbiased Symmetric Matrix Estimator for Topology Inference under Partial Observability

Network topology inference is a fundamental problem in many applications of network science, such as locating the source of fake news, brain connectivity networks detection, etc. Many real-world situations suffer from a critical problem that only a limited part of observed nodes are available. This letter considers the problem of network topology inference under the framework of partial observability. Based on the vector autoregressive model, we propose a novel unbiased estimator for the symmetric network topology with the Gaussian noise and the Laplacian combination rule. Theoretically, we prove that it converges to the network combination matrix in probability. Furthermore, by utilizing the Gaussian mixture model algorithm, an effective algorithm called network inference Gauss algorithm is developed to infer the network structure. Finally, compared with the state-of-the-art methods, numerical experiments demonstrate the proposed algorithm enjoys better performance in the case of small sample sizes.

stat.AP↗

arXiv2021

Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering

The current state-of-the-art generative models for open-domain question answering (ODQA) have focused on generating direct answers from unstructured textual information. However, a large amount of world's knowledge is stored in structured databases, and need to be accessed using query languages such as SQL. Furthermore, query languages can answer questions that require complex reasoning, as well as offering full explainability. In this paper, we propose a hybrid framework that takes both textual and tabular evidence as input and generates either direct answers or SQL queries depending on which form could better answer the question. The generated SQL queries can then be executed on the associated databases to obtain the final answers. To the best of our knowledge, this is the first paper that applies Text2SQL to ODQA tasks. Empirically, we demonstrate that on several ODQA datasets, the hybrid methods consistently outperforms the baseline models that only take homogeneous input by a large margin. Specifically we achieve state-of-the-art performance on OpenSQuAD dataset using a T5-base model. In a detailed analysis, we demonstrate that the being able to generate structural SQL queries can always bring gains, especially for those questions that requires complex reasoning.

cs.CL↗

arXiv2021

Towards Understanding the Impact of Model Size on Differential Private Classification

Differential privacy (DP) is an essential technique for privacy-preserving. It was found that a large model trained for privacy preserving performs worse than a smaller model (e.g. ResNet50 performs worse than ResNet18). To better understand this phenomenon, we study high dimensional DP learning from the viewpoint of generalization. Theoretically, we show that for the simple Gaussian model with even small DP noise, if the dimension is large enough, then the classification error can be as bad as the random guessing. Then we propose a feature selection method to reduce the size of the model, based on a new metric which trades off the classification accuracy and privacy preserving. Experiments on real data support our theoretical results and demonstrate the advantage of the proposed method.

cs.LG↗

arXiv2021

Federated Semi-Supervised Learning with Class Distribution Mismatch

Many existing federated learning (FL) algorithms are designed for supervised learning tasks, assuming that the local data owned by the clients are well labeled. However, in many practical situations, it could be difficult and expensive to acquire complete data labels. Federated semi-supervised learning (Fed-SSL) is an attractive solution for fully utilizing both labeled and unlabeled data. Similar to that encountered in federated supervised learning, class distribution of labeled/unlabeled data could be non-i.i.d. among clients. Besides, in each client, the class distribution of labeled data may be distinct from that of unlabeled data. Unfortunately, both can severely jeopardize the FL performance. To address such challenging issues, we introduce two proper regularization terms that can effectively alleviate the class distribution mismatch problem in Fed-SSL. In addition, to overcome the non-i.i.d. data, we leverage the variance reduction and normalized averaging techniques to develop a novel Fed-SSL algorithm. Theoretically, we prove that the proposed method has a convergence rate of $\mathcal{O}(1/\sqrt{T})$, where $T$ is the number of communication rounds, even when the data distribution are non-i.i.d. among clients. To the best of our knowledge, it is the first formal convergence result for Fed-SSL problems. Numerical experiments based on MNIST data and CIFAR-10 data show that the proposed method can greatly improve the classification accuracy compared to baselines.

cs.LG↗

arXiv2021

End-to-End Cross-Domain Text-to-SQL Semantic Parsing with Auxiliary Task

In this work, we focus on two crucial components in the cross-domain text-to-SQL semantic parsing task: schema linking and value filling. To encourage the model to learn better encoding ability, we propose a column selection auxiliary task to empower the encoder with the relevance matching capability by using explicit learning targets. Furthermore, we propose two value filling methods to build the bridge from the existing zero-shot semantic parsers to real-world applications, considering most of the existing parsers ignore the values filling in the synthesized SQL. With experiments on Spider, our proposed framework improves over the baselines on the execution accuracy and exact set match accuracy when database contents are unavailable, and detailed analysis sheds light on future work.

cs.CL↗

arXiv2021

Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction

In open-domain question answering, questions are highly likely to be ambiguous because users may not know the scope of relevant topics when formulating them. Therefore, a system needs to find possible interpretations of the question, and predict one or multiple plausible answers. When multiple plausible answers are found, the system should rewrite the question for each answer to resolve the ambiguity. In this paper, we present a model that aggregates and combines evidence from multiple passages to adaptively predict a single answer or a set of question-answer pairs for ambiguous questions. In addition, we propose a novel round-trip prediction approach to iteratively generate additional interpretations that our model fails to find in the first pass, and then verify and filter out the incorrect question-answer pairs to arrive at the final disambiguated output. Our model, named Refuel, achieves a new state-of-the-art performance on the AmbigQA dataset, and shows competitive performance on NQ-Open and TriviaQA. The proposed round-trip prediction is a model-agnostic general approach for answering ambiguous open-domain questions, which improves our Refuel as well as several baseline models. We release source code for our models and experiments at https://github.com/amzn/refuel-open-domain-qa.

cs.CL↗

arXiv2021

Improving Factual Consistency of Abstractive Summarization via Question Answering

A commonly observed problem with the state-of-the art abstractive summarization models is that the generated summaries can be factually inconsistent with the input documents. The fact that automatic summarization may produce plausible-sounding yet inaccurate summaries is a major concern that limits its wide application. In this paper we present an approach to address factual consistency in summarization. We first propose an efficient automatic evaluation metric to measure factual consistency; next, we propose a novel learning algorithm that maximizes the proposed metric during model training. Through extensive experiments, we confirm that our method is effective in improving factual consistency and even overall quality of the summaries, as judged by both automatic metrics and human evaluation.

cs.CL↗

arXiv2021

Randomized Multiple Model Multiple Hypothesis Tracking

This paper considers the data association problem for multi-target tracking. Multiple hypothesis tracking is a popular algorithm for solving this problem but it is NP-hard and is is quite complicated for a large number of targets or for tracking maneuvering targets. To improve tracking performance and enhance robustness, we propose a randomized multiple model multiple hypothesis tracking method, which has three distinctive advantages. First, it yields a randomized data association solution which maximizes the expectation of the logarithm of the posterior probability and can be solved efficiently by linear programming. Next, the state estimation performance is improved by the random coefficient matrices Kalman filter, which mitigates the difficulty introduced by randomized data association, i.e., where the coefficient matrices of the dynamic system are random. Third, the probability that the target follows a specific dynamic model is derived by jointly optimizing the multiple possible models and data association hypotheses, and it does not require prior mode transition probabilities. Thus, it is more robust for tracking multiple maneuvering targets. Simulations demonstrate the efficiency and superior results of the proposed algorithm over interacting multiple model multiple hypothesis tracking.

cs.IT↗

arXiv2021

Entity-level Factual Consistency of Abstractive Text Summarization

A key challenge for abstractive summarization is ensuring factual consistency of the generated summary with respect to the original document. For example, state-of-the-art models trained on existing datasets exhibit entity hallucination, generating names of entities that are not present in the source document. We propose a set of new metrics to quantify the entity-level factual consistency of generated summaries and we show that the entity hallucination problem can be alleviated by simply filtering the training data. In addition, we propose a summary-worthy entity classification task to the training process as well as a joint entity and summary generation approach, which yield further improvements in entity level metrics.

cs.CL↗