Search Results for author:
Found 45 papers, 10 papers with code
Rethinking Masked Language Modeling for Chinese Spelling Correction
In this paper, we study Chinese Spelling Correction (CSC) as a joint decision made by two separate models: a language model and an error model.
Automatically Segment the Left Atrium and Scars from LGE-MRIs Using a Boundary-focused nnU-Net
Accurate segmentation of the left atrial (LA) and LA scars can provide valuable information to predict treatment outcomes in AF.
A Theory on Adam Instability in Large-Scale Machine Learning
We present a theory for the previously unexplained divergent behavior noticed in the training of large language models.
Visual Information Matters for ASR Error Correction
Aiming to improve the Automatic Speech Recognition (ASR) outputs with a post-processing step, ASR error correction (EC) techniques have been widely developed due to their efficiency in using parallel text data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Mining User-aware Multi-relations for Fake News Detection in Large Scale Online Social Networks
In this paper, we construct a dual-layer graph (i. e., the news layer and the user layer) to extract multiple relations of news and users in social networks to derive rich information for detecting fake news.
LegalRelectra: Mixed-domain Language Modeling for Long-range Legal Text Comprehension
We show that our model improves over general-domain and single-domain medical and legal language models when processing mixed-domain (personal injury) text.
Transfer Deep Reinforcement Learning-based Large-scale V2G Continuous Charging Coordination with Renewable Energy Sources
Due to the increasing popularity of electric vehicles (EVs) and the technological advancement of EV electronics, the vehicle-to-grid (V2G) technique and large-scale scheduling algorithms have been developed to achieve a high level of renewable energy and power grid stability.
Distributed Estimation for Interconnected Systems with Arbitrary Coupling Structures
By merging these subsystem-level stability conditions and the optimization-based estimator gain design, the distributed, stable and optimal estimators are proposed.
The Influence of Data Pre-processing and Post-processing on Long Document Summarization
Long document summarization is an important and hard task in the field of natural language processing.
Kalman-Like Filter under Binary Sensors
When considering linear dynamic systems, a conservative estimation error covariance with adjustable parameters is constructed by matrix inequality, and then an optimal filter gain is derived by minimizing its trace.
Vision-Guided Quadrupedal Locomotion in the Wild with Multi-Modal Delay Randomization
While Reinforcement Learning (RL) provides a promising paradigm for agile locomotion skills with vision inputs in simulation, it is still very challenging to deploy the RL policy in the real world.
Exploring Retraining-Free Speech Recognition for Intra-sentential Code-Switching
To achieve such an ambitious goal, new mechanisms for foreign pronunciation generation and language model (LM) enrichment have been devised.
Value-Agnostic Conversational Semantic Parsing
Conversational semantic parsers map user utterances to executable programs given dialogue histories composed of previous utterances, programs, and system responses.
Adversarial example generation with AdaBelief Optimizer and Crop Invariance
ABI-FGM and CIM can be readily integrated to build a strong gradient-based attack to further boost the success rates of adversarial examples for black-box attacks.
Task-Oriented Dialogue as Dataflow Synthesis
We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph.
The estimate of sensitivity for large infrared telescopes based on measured sky brightness and atmospheric extinction
In order to evaluate the ground-based infrared telescope sensitivity affected by the noise from the atmosphere, instruments and detectors, we construct a sensitivity model that can calculate limiting magnitudes and signal-to-noise ratio ($S/N$).
Instrumentation and Methods for Astrophysics
On Localized Discrepancy for Domain Adaptation
Finally, we further extend the localized discrepancies for achieving super transfer and derive generalization bounds that could be even more sample-efficient on source domain.
HPC AI500: A Benchmark Suite for HPC AI Systems
In this paper, we propose HPC AI500 --- a benchmark suite for evaluating HPC systems that running scientific DL workloads.
Acquiring Structured Temporal Representation via Crowdsourcing: A Feasibility Study
Temporal Dependency Trees are a structured temporal representation that represents temporal relations among time expressions and events in a text as a dependency tree structure.
Bridging Theory and Algorithm for Domain Adaptation
We introduce Margin Disparity Discrepancy, a novel measurement with rigorous generalization bounds, tailored to the distribution comparison with the asymmetric margin loss, and to the minimax optimization for easier training.
Defending against Whitebox Adversarial Attacks via Randomized Discretization
Adversarial perturbations dramatically decrease the accuracy of state-of-the-art image classifiers.
Neural Ranking Models for Temporal Dependency Structure Parsing
In a parsing-only evaluation setup where gold time expressions and events are provided, our parser reaches 0. 81 and 0. 70 f-score on unlabeled and labeled parsing respectively, a result that is very competitive against alternative approaches.
Structured Interpretation of Temporal Relations
Temporal relations between events and time expressions in a document are often modeled in an unstructured manner where relations between individual pairs of time expressions and events are considered in isolation.
Macro Grammars and Holistic Triggering for Efficient Semantic Parsing
To learn a semantic parser from denotations, a learning algorithm must search over a combinatorially large space of logical forms for ones consistent with the annotated denotations.
A Hitting Time Analysis of Stochastic Gradient Langevin Dynamics
We study the Stochastic Gradient Langevin Dynamics (SGLD) algorithm for non-convex optimization.
Convexified Convolutional Neural Networks
For learning two-layer convolutional neural networks, we prove that the generalization error obtained by a convexified CNN converges to that of the best possible CNN.
Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequences
Our first main result shows that the population likelihood function has bad local maxima even in the special case of equally-weighted mixtures of well-separated and spherical Gaussians.
Learning Halfspaces and Neural Networks with Random Initialization
For loss functions that are $L$-Lipschitz continuous, we present algorithms to learn halfspaces and multi-layer neural networks that achieve arbitrarily small excess risk $\epsilon>0$.
$\ell_1$-regularized Neural Networks are Improperly Learnable in Polynomial Time
The sample complexity and the time complexity of the presented method are polynomial in the input dimension and in $(1/\epsilon,\log(1/\delta), F(k, L))$, where $F(k, L)$ is a function depending on $(k, L)$ and on the activation function, independent of the number of neurons.
Splash: User-friendly Programming Interface for Parallelizing Stochastic Algorithms
Splash consists of a programming interface and an execution engine.
Optimal prediction for sparse linear models? Lower bounds for coordinate-separable M-estimators
In this paper, we show that the slow rate is intrinsic to a broad class of M-estimators.
Distributed Estimation of Generalized Matrix Rank: Efficient Algorithms and Lower Bounds
We study the following generalized matrix rank estimation problem: given an $n \times n$ matrix and a constant $c \geq 0$, estimate the number of eigenvalues that are greater than $c$.
Communication-Efficient Distributed Optimization of Self-Concordant Empirical Loss
We consider distributed convex optimization problems originated from sample average approximation of stochastic optimization, or empirical risk minimization in machine learning.
Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization
We consider a generic convex optimization problem associated with regularized empirical risk minimization of linear predictors.
Spectral Methods meet EM: A Provably Optimal Algorithm for Crowdsourcing
Crowdsourcing is a popular paradigm for effectively collecting labels at low cost.
Optimality guarantees for distributed statistical estimation
Large data sets often require performing distributed statistical estimation, with a full data set split across multiple machines and limited communication between machines.
Buy one get one free: Distant annotation of Chinese tense, event type and modality
We describe a {``}distant annotation{''} method where we mark up the semantic tense, event type, and modality of Chinese events via a word-aligned parallel corpus.
Information-theoretic lower bounds for distributed statistical estimation with communication constraints
We establish minimax risk lower bounds for distributed statistical estimation given a budget $B$ of the total number of bits that may be communicated.
Divide and Conquer Kernel Ridge Regression: A Distributed Algorithm with Minimax Optimal Rates
We establish optimal convergence rates for a decomposition-based scalable approach to kernel ridge regression.
Communication-Efficient Algorithms for Statistical Optimization
The first algorithm is an averaging method that distributes the $N$ data samples evenly to $m$ machines, performs separate minimization on each subset, and then averages the estimates.
Comunication-Efficient Algorithms for Statistical Optimization
We analyze two communication-efficient algorithms for distributed statistical optimization on large-scale data sets.
