arXiv subjects

Chang Su

Publications and source records attributed to Chang Su.

47 records · Page 3Linked to original sources

arXiv2022

Mechanism, measurement, and quantification of stress in decision process: a model based systematic-review protocol

Every human action begins with decision-making. Stress is a significant source of biases that can influence human decision-making. In order to understand the relationship between stress and decision-making, stress quantification is fundamental. Different methods of measuring and quantifying stress in decision-making have been described in the literature while an up-to-date systematic review of the existing methods is lacking. Moreover, mental stress, mental effort, cognitive workload, and workload are often used interchangeably but should be distinguished to enable in-depth investigations of decision-mechanisms. Our objectives are to clarify stress related concepts and review the measurement, quantification, and application of stress during decision making activities.

cs.HC↗

arXiv2021

Diformer: Directional Transformer for Neural Machine Translation

Autoregressive (AR) and Non-autoregressive (NAR) models have their own superiority on the performance and latency, combining them into one model may take advantage of both. Current combination frameworks focus more on the integration of multiple decoding paradigms with a unified generative model, e.g. Masked Language Model. However, the generalization can be harmful to the performance due to the gap between training objective and inference. In this paper, we aim to close the gap by preserving the original objective of AR and NAR under a unified framework. Specifically, we propose the Directional Transformer (Diformer) by jointly modelling AR and NAR into three generation directions (left-to-right, right-to-left and straight) with a newly introduced direction variable, which works by controlling the prediction of each token to have specific dependencies under that direction. The unification achieved by direction successfully preserves the original dependency assumption used in AR and NAR, retaining both generalization and performance. Experiments on 4 WMT benchmarks demonstrate that Diformer outperforms current united-modelling works with more than 1.5 BLEU points for both AR and NAR decoding, and is also competitive to the state-of-the-art independent AR and NAR models.

cs.CL↗

arXiv2021

Self-Distillation Mixup Training for Non-autoregressive Neural Machine Translation

Recently, non-autoregressive (NAT) models predict outputs in parallel, achieving substantial improvements in generation speed compared to autoregressive (AT) models. While performing worse on raw data, most NAT models are trained as student models on distilled data generated by AT teacher models, which is known as sequence-level Knowledge Distillation. An effective training strategy to improve the performance of AT models is Self-Distillation Mixup (SDM) Training, which pre-trains a model on raw data, generates distilled data by the pre-trained model itself and finally re-trains a model on the combination of raw data and distilled data. In this work, we aim to view SDM for NAT models, but find directly adopting SDM to NAT models gains no improvements in terms of translation quality. Through careful analysis, we observe the invalidation is correlated to Modeling Diversity and Confirmation Bias between the AT teacher model and the NAT student models. Based on these findings, we propose an enhanced strategy named SDMRT by adding two stages to classic SDM: one is Pre-Rerank on self-distilled data, the other is Fine-Tune on Filtered teacher-distilled data. Our results outperform baselines by 0.6 to 1.2 BLEU on multiple NAT models. As another bonus, for Iterative Refinement NAT models, our methods can outperform baselines within half iteration number, which means 2X acceleration.

cs.CL↗

arXiv2021

Joint-training on Symbiosis Networks for Deep Nueral Machine Translation models

Deep encoders have been proven to be effective in improving neural machine translation (NMT) systems, but it reaches the upper bound of translation quality when the number of encoder layers exceeds 18. Worse still, deeper networks consume a lot of memory, making it impossible to train efficiently. In this paper, we present Symbiosis Networks, which include a full network as the Symbiosis Main Network (M-Net) and another shared sub-network with the same structure but less layers as the Symbiotic Sub Network (S-Net). We adopt Symbiosis Networks on Transformer-deep (m-n) architecture and define a particular regularization loss $\mathcal{L}_τ$ between the M-Net and S-Net in NMT. We apply joint-training on the Symbiosis Networks and aim to improve the M-Net performance. Our proposed training strategy improves Transformer-deep (12-6) by 0.61, 0.49 and 0.69 BLEU over the baselines under classic training on WMT'14 EN->DE, DE->EN and EN->FR tasks. Furthermore, our Transformer-deep (12-6) even outperforms classic Transformer-deep (18-6).

cs.CL↗

arXiv2021

Empirical Bayes PCA in high dimensions

When the dimension of data is comparable to or larger than the number of data samples, Principal Components Analysis (PCA) may exhibit problematic high-dimensional noise. In this work, we propose an Empirical Bayes PCA method that reduces this noise by estimating a joint prior distribution for the principal components. EB-PCA is based on the classical Kiefer-Wolfowitz nonparametric MLE for empirical Bayes estimation, distributional results derived from random matrix theory for the sample PCs, and iterative refinement using an Approximate Message Passing (AMP) algorithm. In theoretical "spiked" models, EB-PCA achieves Bayes-optimal estimation accuracy in the same settings as an oracle Bayes AMP procedure that knows the true priors. Empirically, EB-PCA significantly improves over PCA when there is strong prior structure, both in simulation and on quantitative benchmarks constructed from the 1000 Genomes Project and the International HapMap Project. An illustration is presented for analysis of gene expression data obtained by single-cell RNA-seq.

stat.ME↗

arXiv2021

The HW-TSC's Offline Speech Translation Systems for IWSLT 2021 Evaluation

This paper describes our work in participation of the IWSLT-2021 offline speech translation task. Our system was built in a cascade form, including a speaker diarization module, an Automatic Speech Recognition (ASR) module and a Machine Translation (MT) module. We directly use the LIUM SpkDiarization tool as the diarization module. The ASR module is trained with three ASR datasets from different sources, by multi-source training, using a modified Transformer encoder. The MT module is pretrained on the large-scale WMT news translation dataset and fine-tuned on the TED corpus. Our method achieves 24.6 BLEU score on the 2021 test set.

cs.CL↗

arXiv2021

Robust Multi-Modal Policies for Industrial Assembly via Reinforcement Learning and Demonstrations: A Large-Scale Study

Over the past several years there has been a considerable research investment into learning-based approaches to industrial assembly, but despite significant progress these techniques have yet to be adopted by industry. We argue that it is the prohibitively large design space for Deep Reinforcement Learning (DRL), rather than algorithmic limitations per se, that are truly responsible for this lack of adoption. Pushing these techniques into the industrial mainstream requires an industry-oriented paradigm which differs significantly from the academic mindset. In this paper we define criteria for industry-oriented DRL, and perform a thorough comparison according to these criteria of one family of learning approaches, DRL from demonstration, against a professional industrial integrator on the recently established NIST assembly benchmark. We explain the design choices, representing several years of investigation, which enabled our DRL system to consistently outperform the integrator baseline in terms of both speed and reliability. Finally, we conclude with a competition between our DRL system and a human on a challenge task of insertion into a randomly moving target. This study suggests that DRL is capable of outperforming not only established engineered approaches, but the human motor system as well, and that there remains significant room for improvement. Videos can be found on our project website: https://sites.google.com/view/shield-nist.

cs.AI↗

arXiv2020

Federated Learning for Healthcare Informatics

With the rapid development of computer software and hardware technologies, more and more healthcare data are becoming readily available from clinical institutions, patients, insurance companies and pharmaceutical industries, among others. This access provides an unprecedented opportunity for data science technologies to derive data-driven insights and improve the quality of care delivery. Healthcare data, however, are usually fragmented and private making it difficult to generate robust results across populations. For example, different hospitals own the electronic health records (EHR) of different patient populations and these records are difficult to share across hospitals because of their sensitive nature. This creates a big barrier for developing effective analytical approaches that are generalizable, which need diverse, "big data". Federated learning, a mechanism of training a shared global model with a central server while keeping all the sensitive data in local institutions where the data belong, provides great promise to connect the fragmented healthcare data sources with privacy-preservation. The goal of this survey is to provide a review for federated learning technologies, particularly within the biomedical space. In particular, we summarize the general solutions to the statistical challenges, system challenges and privacy issues in federated learning, and point out the implications and potentials in healthcare.

cs.LG↗

arXiv2020

Well-posedness for good Boussinesq equations subject to quasi-periodic initial data

This paper concerns the local well-posedness for the "good" Boussinesq equation subject to quasi-periodic initial conditions. By constructing a delicately and subtly iterative process together with an explicit combinatorial analysis, we show that there exists a unique solution for such a model in a small region of time. The size of this region depends on both the given data and the frequency vector involved. Moreover the local solution has an expansion with exponentially decaying Fourier coefficients.

math.AP↗

arXiv2019

GRAPHENE: A Precise Biomedical Literature Retrieval Engine with Graph Augmented Deep Learning and External Knowledge Empowerment

Effective biomedical literature retrieval (BLR) plays a central role in precision medicine informatics. In this paper, we propose GRAPHENE, which is a deep learning based framework for precise BLR. GRAPHENE consists of three main different modules 1) graph-augmented document representation learning; 2) query expansion and representation learning and 3) learning to rank biomedical articles. The graph-augmented document representation learning module constructs a document-concept graph containing biomedical concept nodes and document nodes so that global biomedical related concept from external knowledge source can be captured, which is further connected to a BiLSTM so both local and global topics can be explored. Query expansion and representation learning module expands the query with abbreviations and different names, and then builds a CNN-based model to convolve the expanded query and obtain a vector representation for each query. Learning to rank minimizes a ranking loss between biomedical articles with the query to learn the retrieval function. Experimental results on applying our system to TREC Precision Medicine track data are provided to demonstrate its effectiveness.

cs.IR↗

arXiv2019

A Multi-View Ensemble Classification Model for Clinically Actionable Genetic Mutations

This paper presents details of our winning solutions to the task IV of NIPS 2017 Competition Track entitled Classifying Clinically Actionable Genetic Mutations. The machine learning task aims to classify genetic mutations based on text evidence from clinical literature with promising performance. We develop a novel multi-view machine learning framework with ensemble classification models to solve the problem. During the Challenge, feature combinations derived from three views including document view, entity text view, and entity name view, which complements each other, are comprehensively explored. As the final solution, we submitted an ensemble of nine basic gradient boosting models which shows the best performance in the evaluation. The approach scores 0.5506 and 0.6694 in terms of logarithmic loss on a fixed split in stage-1 testing phase and 5-fold cross validation respectively, which also makes us ranked as a top-1 team out of more than 1,300 solutions in NIPS 2017 Competition Track IV.

cs.LG↗