Yu-hui Chen

Yu-hui Chen

I joined Google at the end of 2015, starting with Smart Imagery team in Geo. Since Feb 2018, I am a member of Medical Brain and Health Research. My works mainly focus on extracting structural information from images/texts and building up infrastructure for powering the development of ML models. My area of interest include computer vision, natural language processing, signal processing, and machine learning.

I received my Ph.D. in Electrical and Computer Engineering from University of Michigan, working with Prof. Alfred Hero on multi-modality image fusion in biomedical and materials in 2015. The main idea of image fusion is to intelligently combine the information from multiple image modalities for better decision making, e.g. detecting anomaly. I received my B.S. in Electrical Engineering from National Taiwan University from 2005 to 2009, working with Prof. Lin-Shan Lee on speech recognition and information retrieval.

Personal:
My hometown is Taipei, Taiwan, where I was born and grew up. I came to United States in 2010 for my graduate degree and started to learn and enjoy snowboarding since then. I love music (classical, Rock, and R&B) and play a little bit piano and drums. Badminton is my favorite sport which I play regularly.
Authored Publications
Google Publications
Other Publications
Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    The Medical Scribe: Corpus Development and Model Performance Analyses
    Amanda Perry
    Ashley Robson Domin
    Chris Co
    Hagen Soltau
    Justin Stuart Paul
    Lauren Keyes
    Linh Tran
    Mark David Knichel
    Mingqiu Wang
    Nan Du
    Rayman Huang
    Proc. Language Resources and Evaluation, 2020
    Preview abstract There has been a growing interest in creating tools to assist clinical note generation from the audio of provider-patient encounters. Motivated by this goal and with the help of providers and experienced medical scribes, we developed an annotation scheme to extract relevant clinical concepts. Using this annotation scheme, a corpus of about 6k clinical encounters was labeled, which was used to train a state-of-the-art tagging model. We report model performance and a detailed analyses of the results. View details
    Extracting Symptoms and their Status from Clinical Conversations
    Nan Du
    Kai Chen
    Linh Tran
    Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy(2019), pp. 915-9125
    Preview abstract This paper describes novel models tailored for a new application, that of extracting the symptoms mentioned in clinical conversations along with their status. Lack of any publicly available corpus in this privacy-sensitive domain led us to develop our own corpus, consisting of about 3K conversations annotated by professional medical scribes. We propose two novel deep learning approaches to infer the symptom names and their status: (1) a new hierarchical span-attribute tagging (SAT) model, trained using curriculum learning, and (2) a variant of sequence-to-sequence model which decodes the symptoms and their status from a few speaker turns within a sliding window over the conversation. This task stems from a realistic application of assisting medical providers in capturing symptoms mentioned by patients from their clinical conversations. To reflect this application, we define multiple metrics. From inter-rater agreement, we find that the task is inherently difficult. We conduct comprehensive evaluations on several contrasting conditions and observe that the performance of the models range from an F-score of 0.5 to 0.8 depending on the condition. Our analysis not only reveals the inherent challenges of the task, but also provides useful directions to improve the models. View details
    Particle Filtering for Slice-to-volume Motion Correction in EPI Based Functional MRI
    Roni Mittelman
    Boklye Kim
    Charles Meyer
    Alfred Hero
    Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on, pp. 679-683
    A Dictionary Approach to Electron Backscatter Diffraction Indexing
    Se Un Park
    Dennis Wei
    Gregory Newstadt
    Michael A. Jackson
    Jeff P. Simmons
    Marc De Graef
    Alfred O. Hero
    Microscopy and Microanalysis, 21(2015), pp. 739-752
    Statistical Estimation and Clustering of Group-invariant Orientation Parameters
    Dennis Wei
    Gregory Newstadt
    Marc De Graef
    Jeffrey Simmons
    Alfred Hero
    Information Fusion (Fusion), 2015 18th International Conference on, pp. 719-726
    Coercive Region-level Registration for Multi-modal Images
    Dennis Wei
    Gregory Newstadt
    Jeffrey Simmons
    Alfred Hero
    Image Processing (ICIP), 2015 IEEE International Conference on, pp. 2419-2423
    Parameter Estimation in Spherical Symmetry Groups
    Dennis Wei
    Gregory Newstadt
    Marc DeGraef
    Jeffrey Simmons
    Alfred Hero
    IEEE Signal Processing Letters, IEEE(2015), pp. 1152-1155
    Preview abstract This paper considers statistical estimation problems where the probability distribution of the observed random variable is invariant with respect to actions of a finite topological group. It is shown that any such distribution must satisfy a restricted finite mixture representation. When specialized to the case of distributions over the sphere that are invariant to the actions of a finite spherical symmetry group G, a groupinvariant extension of the Von Mises Fisher (VMF) distribution is obtained. The G-invariant VMF is parameterized by location and scale parameters that specify the distribution’s mean orientation and its concentration about the mean, respectively. Using the restricted finite mixture representation these parameters can be estimated using an Expectation Maximization (EM) maximum likelihood (ML) estimation algorithm. This is illustrated for the problem of mean crystal orientation estimation under the spherically symmetric group associated with the crystal form, e.g., cubic or octahedral or hexahedral. Simulations and experiments establish the advantages of the extended VMF EM-ML estimator for data acquired by Electron Backscatter Diffraction (EBSD) microscopy of a polycrystalline Nickel alloy sample. View details
    An Initial Attempt to Improve Spoken Term Detection by Learning Optimal Weights for Different Indexing Features
    Chia-Chen Chou
    Hung-Yi Lee
    Lin-Shan Lee
    Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on, pp. 5278-5281