Search Results for author: Hong Yu

Found 102 papers, 41 papers with code

Generation of Patient After-Visit Summaries to Support Physicians

1 code implementation COLING 2022 Pengshan Cai, Fei Liu, Adarsha Bajracharya, Joe Sills, Alok Kapoor, Weisong Liu, Dan Berlowitz, David Levy, Richeek Pradhan, Hong Yu

Crucially, we introduce a feedback mechanism that alerts physicians when an automatic summary fails to capture the important details of the clinical notes or when it contains hallucinated facts that are potentially detrimental to the summary quality.

Management

ReadCtrl: Personalizing text generation with readability-controlled instruction learning

no code implementations13 Jun 2024 Hieu Tran, Zonghai Yao, Lingxi Li, Hong Yu

In an era of large language models (LLMs), readability-controlled text generation based on LLMs has become increasingly important.

Text Generation

Synth-SBDH: A Synthetic Dataset of Social and Behavioral Determinants of Health for Clinical Text

1 code implementation10 Jun 2024 Avijit Mitra, Emily Druhl, Raelene Goodwin, Hong Yu

Social and behavioral determinants of health (SBDH) play a crucial role in health outcomes and are frequently documented in clinical text.

ReALM: Reference Resolution As Language Modeling

no code implementations29 Mar 2024 Joel Ruben Antony Moniz, Soundarya Krishnan, Melis Ozyildirim, Prathamesh Saraf, Halim Cagri Ates, Yuan Zhang, Hong Yu, Nidhi Rajshree

Reference resolution is an important problem, one that is essential to understand and successfully handle context of different kinds.

Language Modelling

ClinicalMamba: A Generative Clinical Language Model on Longitudinal Clinical Notes

1 code implementation9 Mar 2024 Zhichao Yang, Avijit Mitra, Sunjae Kwon, Hong Yu

The advancement of natural language processing (NLP) systems in healthcare hinges on language model ability to interpret the intricate information contained within clinical notes.

Few-Shot Learning Language Modelling

JMLR: Joint Medical LLM and Retrieval Training for Enhancing Reasoning and Professional Question Answering Capability

1 code implementation27 Feb 2024 Junda Wang, Zhichao Yang, Zonghai Yao, Hong Yu

Unlike previous methods in RAG where the retrieval model was trained separately from the LLM, we introduce JMLR (for Jointly trains LLM and information Retrieval (IR)) during the fine-tuning phase.

Information Retrieval Question Answering +1

SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization

1 code implementation21 Feb 2024 Prakamya Mishra, Zonghai Yao, Parth Vashisht, Feiyun ouyang, Beining Wang, Vidhi Dhaval Mody, Hong Yu

Large Language Models (LLMs) such as GPT & Llama have demonstrated significant achievements in summarization tasks but struggle with factual inaccuracies, a critical issue in clinical NLP applications where errors could lead to serious consequences.

LocalTweets to LocalHealth: A Mental Health Surveillance Framework Based on Twitter Data

no code implementations21 Feb 2024 Vijeta Deshpande, Minhwa Lee, Zonghai Yao, Zihao Zhang, Jason Brian Gibbons, Hong Yu

Prior research on Twitter (now X) data has provided positive evidence of its utility in developing supplementary health surveillance systems.

SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Tracking

no code implementations3 Feb 2024 Atharva Kulkarni, Bo-Hsiang Tseng, Joel Ruben Antony Moniz, Dhivya Piraviperumal, Hong Yu, Shruti Bhargava

Remarkably, our few-shot learning approach recovers nearly $98%$ of the performance compared to the few-shot setup using human-annotated training data.

dialog state tracking Few-Shot Learning +2

HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text

1 code implementation NeurIPS 2023 Han Liu, Zhi Xu, Xiaotong Zhang, Feng Zhang, Fenglong Ma, Hongyang Chen, Hong Yu, Xianchao Zhang

Black-box hard-label adversarial attack on text is a practical and challenging task, as the text data space is inherently discrete and non-differentiable, and only the predicted label is accessible.

Adversarial Attack Hard-label Attack +5

Can Large Language Models Understand Context?

no code implementations1 Feb 2024 YIlun Zhu, Joel Ruben Antony Moniz, Shruti Bhargava, Jiarui Lu, Dhivya Piraviperumal, Site Li, Yuan Zhang, Hong Yu, Bo-Hsiang Tseng

Understanding context is key to understanding human language, an ability which Large Language Models (LLMs) have been increasingly seen to demonstrate to an impressive extent.

In-Context Learning Quantization

EHR Interaction Between Patients and AI: NoteAid EHR Interaction

no code implementations29 Dec 2023 Xiaocheng Zhang, Zonghai Yao, Hong Yu

Through a comprehensive evaluation of the entire dataset using LLM assessment and a rigorous manual evaluation of 64 instances, we showcase the potential of LLMs in patient education.

README: Bridging Medical Jargon and Lay Understanding for Patient Education through Data-Centric NLP

1 code implementation24 Dec 2023 Zonghai Yao, Nandyala Siddharth Kantu, Guanghao Wei, Hieu Tran, Zhangqi Duan, Sunjae Kwon, Zhichao Yang, README annotation team, Hong Yu

The advancement in healthcare has shifted focus toward patient-centric approaches, particularly in self-care and patient education, facilitated by access to Electronic Health Records (EHR).

Two Directions for Clinical Data Generation with Large Language Models: Data-to-Label and Label-to-Data

no code implementations9 Dec 2023 Rumeng Li, Xun Wang, Hong Yu

We train a system to detect AD-related signs and symptoms from EHRs, using three datasets: (1) a gold dataset annotated by human experts on longitudinal EHRs of AD patients; (2) a silver dataset created by the data-to-label method; and (3) a bronze dataset created by the label-to-data method.

Do Physicians Know How to Prompt? The Need for Automatic Prompt Optimization Help in Clinical Note Generation

no code implementations16 Nov 2023 Zonghai Yao, Ahmed Jaafar, Beining Wang, Zhichao Yang, Hong Yu

We recommend a two-phase optimization process, leveraging APO-GPT4 for consistency and expert input for personalization.

Prompt Engineering

Large Language Models are In-context Teachers for Knowledge Reasoning

no code implementations12 Nov 2023 Jiachen Zhao, Zonghai Yao, Zhichao Yang, Hong Yu

However, human experts are usually required to craft demonstrations for in-context learning (ICL), which is expensive and has high variance.

In-Context Learning Information Retrieval +3

Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization

1 code implementation30 Oct 2023 Prakamya Mishra, Zonghai Yao, Shuwei Chen, Beining Wang, Rohan Mittal, Hong Yu

In this work, we propose a new pipeline using ChatGPT instead of human experts to generate high-quality feedback data for improving factual consistency in the clinical note summarization task.

Hallucination

EHRTutor: Enhancing Patient Understanding of Discharge Instructions

no code implementations30 Oct 2023 Zihao Zhang, Zonghai Yao, Huixue Zhou, Feiyun ouyang, Hong Yu

This paper presents EHRTutor, an innovative multi-component framework leveraging the Large Language Model (LLM) for patient education through conversational question-answering.

Conversational Question Answering Language Modelling +1

Boosting Decision-Based Black-Box Adversarial Attack with Gradient Priors

no code implementations29 Oct 2023 Han Liu, Xingshuo Huang, Xiaotong Zhang, Qimai Li, Fenglong Ma, Wei Wang, Hongyang Chen, Hong Yu, Xianchao Zhang

Decision-based methods have shown to be effective in black-box adversarial attacks, as they can obtain satisfactory performance and only require to access the final model prediction.

Adversarial Attack

STEER: Semantic Turn Extension-Expansion Recognition for Voice Assistants

no code implementations25 Oct 2023 Leon Liyang Zhang, Jiarui Lu, Joel Ruben Antony Moniz, Aditya Kulkarni, Dhivya Piraviperumal, Tien Dung Tran, Nicholas Tzou, Hong Yu

In the context of a voice assistant system, steering refers to the phenomenon in which a user issues a follow-up command attempting to direct or clarify a previous turn.

Sentence

NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes

1 code implementation24 Oct 2023 Junda Wang, Zonghai Yao, Zhichao Yang, Huixue Zhou, Rumeng Li, Xun Wang, Yucheng Xu, Hong Yu

We introduce NoteChat, a novel cooperative multi-agent framework leveraging Large Language Models (LLMs) to generate patient-physician dialogues.

Dialogue Generation

PaniniQA: Enhancing Patient Education Through Interactive Question Answering

1 code implementation7 Aug 2023 Pengshan Cai, Zonghai Yao, Fei Liu, Dakuo Wang, Meghan Reilly, Huixue Zhou, Lingxi Li, Yi Cao, Alok Kapoor, Adarsha Bajracharya, Dan Berlowitz, Hong Yu

Patient portal allows discharged patients to access their personalized discharge instructions in electronic health records (EHRs).

Question Answering

Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Data

1 code implementation26 Jul 2023 Xuhai Xu, Bingsheng Yao, Yuanzhe Dong, Saadia Gabriel, Hong Yu, James Hendler, Marzyeh Ghassemi, Anind K. Dey, Dakuo Wang

More importantly, our experiments show that instruction finetuning can significantly boost the performance of LLMs for all tasks simultaneously.

Language Modelling

Early Prediction of Alzheimers Disease Leveraging Symptom Occurrences from Longitudinal Electronic Health Records of US Military Veterans

no code implementations23 Jul 2023 Rumeng Li, Xun Wang, Dan Berlowitz, Brian Silver, Wen Hu, Heather Keating, Raelene Goodwin, Weisong Liu, Honghuang Lin, Hong Yu

We used a panel of AD-related keywords and their occurrences over time in a patient's longitudinal EHRs as predictors for AD prediction with four machine learning models.

ODD: A Benchmark Dataset for the Natural Language Processing based Opioid Related Aberrant Behavior Detection

1 code implementation5 Jul 2023 Sunjae Kwon, Xun Wang, Weisong Liu, Emily Druhl, Minhee L. Sung, Joel I. Reisman, Wenjun Li, Robert D. Kerns, William Becker, Hong Yu

Experimental results show that the prompt-tuning models outperformed the fine-tuning models in most categories and the gains were especially higher among uncommon categories (Suggested Aberrant Behavior, Confirmed Aberrant Behaviors, Diagnosed Opioid Dependence, and Medication Change).

UMASS_BioNLP at MEDIQA-Chat 2023: Can LLMs generate high-quality synthetic note-oriented doctor-patient conversations?

1 code implementation29 Jun 2023 Junda Wang, Zonghai Yao, Avijit Mitra, Samuel Osebe, Zhichao Yang, Hong Yu

This paper presents UMASS_BioNLP team participation in the MEDIQA-Chat 2023 shared task for Task-A and Task-C. We focus especially on Task-C and propose a novel LLMs cooperation system named a doctor-patient loop to generate high-quality conversation data sets.

Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond

1 code implementation20 May 2023 Haw-Shiuan Chang, Zonghai Yao, Alolika Gon, Hong Yu, Andrew McCallum

Is the output softmax layer, which is adopted by most language models (LMs), always the best way to compute the next word probability?

Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss Information

1 code implementation2 May 2023 Sunjae Kwon, Rishabh Garodia, Minhwa Lee, Zhichao Yang, Hong Yu

Specifically, we suggest employing Bayesian inference to incorporate the sense definitions when sense information of the answer is not provided.

Bayesian Inference Image-text matching +2

Boosting Few-Shot Text Classification via Distribution Estimation

no code implementations26 Mar 2023 Han Liu, Feng Zhang, Xiaotong Zhang, Siyang Zhao, Fenglong Ma, Xiao-Ming Wu, Hongyang Chen, Hong Yu, Xianchao Zhang

Distribution estimation has been demonstrated as one of the most effective approaches in dealing with few-shot image classification, as the low-level patterns and underlying representations can be easily transferred across different tasks in computer vision domain.

Few-Shot Image Classification Few-Shot Text Classification +1

Enhancing the prediction of disease outcomes using electronic health records and pretrained deep learning models

no code implementations22 Dec 2022 Zhichao Yang, Weisong Liu, Dan Berlowitz, Hong Yu

Question: Can an encoder-decoder architecture pretrained on a large dataset of longitudinal electronic health records improves patient outcome predictions?

Decoder Denoising

Automated Identification of Eviction Status from Electronic Health Record Notes

1 code implementation6 Dec 2022 Zonghai Yao, Jack Tsai, Weisong Liu, David A. Levy, Emily Druhl, Joel I Reisman, Hong Yu

Materials and Methods: We first defined eviction status (eviction presence and eviction period) and then annotated eviction status in 5000 EHR notes from the Veterans Health Administration (VHA).

An Automatic SOAP Classification System Using Weakly Supervision And Transfer Learning

no code implementations26 Nov 2022 Sunjae Kwon, Zhichao Yang, Hong Yu

The transfer learning framework helps SOAP classification model's inter-hospital migration with a minimal size of the manually annotated dataset.

Classification Language Modelling +1

Multi-label Few-shot ICD Coding as Autoregressive Generation with Prompt

1 code implementation24 Nov 2022 Zhichao Yang, Sunjae Kwon, Zonghai Yao, Hong Yu

This task is challenging due to the high-dimensional space of multi-label assignment (155, 000+ ICD code candidates) and the long-tail challenge - Many ICD codes are infrequently assigned yet infrequent ICD codes are important clinically.

Multi-Label Classification

Context Variance Evaluation of Pretrained Language Models for Prompt-based Biomedical Knowledge Probing

no code implementations18 Nov 2022 Zonghai Yao, Yi Cao, Zhichao Yang, Hong Yu

Different from the previous known-unknown evaluation criteria, we propose the concept of "Misunderstand" in LAMA for the first time.

Knowledge Probing

Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Coding

1 code implementation7 Oct 2022 Zhichao Yang, Shufan Wang, Bhanu Pratap Singh Rawat, Avijit Mitra, Hong Yu

Automatic International Classification of Diseases (ICD) coding aims to assign multiple ICD codes to a medical note with average length of 3, 000+ tokens.

Contrastive Learning Medical Code Prediction

Extracting Biomedical Factual Knowledge Using Pretrained Language Model and Electronic Health Record Context

no code implementations26 Aug 2022 Zonghai Yao, Yi Cao, Zhichao Yang, Vijeta Deshpande, Hong Yu

In order to make LMs as KBs more in line with the actual application scenarios of the biomedical domain, we specifically add EHR notes as context to the prompt to improve the low bound in the biomedical domain.

Language Modelling

Advanced Conditional Variational Autoencoders (A-CVAE): Towards interpreting open-domain conversation generation via disentangling latent feature representation

no code implementations26 Jul 2022 Ye Wang, Jingbo Liao, Hong Yu, Guoyin Wang, Xiaoxia Zhang, Li Liu

Particularly, the model integrates the macro-level guided-category knowledge and micro-level open-domain dialogue data for the training, leveraging the priori knowledge into the latent space, which enables the model to disentangle the latent variables within the mesoscopic scale.

Disentanglement

Hyperspectral image reconstruction for spectral camera based on ghost imaging via sparsity constraints using V-DUnet

no code implementations28 Jun 2022 Ziyan Chen, Zhentao Liu, Chenyu Hu, Heng Wu, Jianrong Wu, Jinda Lin, Zhishen Tong, Hong Yu, Shensheng Han

When applying deep learning into GISC spectral camera, there are several challenges need to be solved: 1) how to deal with the large amount of 3D hyperspectral data, 2) how to reduce the influence caused by the uncertainty of the random reference measurements, 3) how to improve the reconstructed image quality as far as possible.

Compressive Sensing Image Reconstruction

Label-enhanced Prototypical Network with Contrastive Learning for Multi-label Few-shot Aspect Category Detection

no code implementations14 Jun 2022 Han Liu, Feng Zhang, Xiaotong Zhang, Siyang Zhao, Junjie Sun, Hong Yu, Xianchao Zhang

Multi-label aspect category detection allows a given review sentence to contain multiple aspect categories, which is shown to be more practical in sentiment analysis and attracting increasing attention.

Aspect Category Detection Contrastive Learning +2

A Simple Meta-learning Paradigm for Zero-shot Intent Classification with Mixture Attention Mechanism

no code implementations5 Jun 2022 Han Liu, Siyang Zhao, Xiaotong Zhang, Feng Zhang, Junjie Sun, Hong Yu, Xianchao Zhang

Zero-shot intent classification is a vital and challenging task in dialogue systems, which aims to deal with numerous fast-emerging unacquainted intents without annotated training data.

Classification intent-classification +4

Learning as Conversation: Dialogue Systems Reinforced for Information Acquisition

1 code implementation NAACL 2022 Pengshan Cai, Hui Wan, Fei Liu, Mo Yu, Hong Yu, Sachindra Joshi

We propose novel AI-empowered chat bots for learning as conversation where a user does not read a passage but gains information and knowledge through conversation with a teacher bot.

ScAN: Suicide Attempt and Ideation Events Dataset

1 code implementation NAACL 2022 Bhanu Pratap Singh Rawat, Samuel Kovaly, Wilfred R. Pigeon, Hong Yu

In this study, we first built Suicide Attempt and Ideation Events (ScAN) dataset, a subset of the publicly available MIMIC III dataset spanning over 12k+ EHR notes with 19k+ annotated SA and SI events information.

Retrieval

Caption Feature Space Regularization for Audio Captioning

1 code implementation18 Apr 2022 Yiming Zhang, Hong Yu, Ruoyi Du, Zhanyu Ma, Yuan Dong

To eliminate this negative effect, in this paper, we propose a two-stage framework for audio captioning: (i) in the first stage, via the contrastive learning, we construct a proxy feature space to reduce the distances between captions correlated to the same audio, and (ii) in the second stage, the proxy feature space is utilized as additional supervision to encourage the model to be optimized in the direction that benefits all the correlated captions.

Audio captioning Contrastive Learning +1

Attention guided global enhancement and local refinement network for semantic segmentation

1 code implementation9 Apr 2022 Jiangyun Li, Sen Zha, Chen Chen, Meng Ding, Tianxiang Zhang, Hong Yu

First, commonly used upsampling methods in the decoder such as interpolation and deconvolution suffer from a local receptive field, unable to encode global contexts.

Decoder Semantic Segmentation

Category Guided Attention Network for Brain Tumor Segmentation in MRI

1 code implementation29 Mar 2022 Jiangyun Li, Hong Yu, Chen Chen, Meng Ding, Sen Zha

In this model, we design a Supervised Attention Module (SAM) based on the attention mechanism, which can capture more accurate and stable long-range dependency in feature maps without introducing much computational cost.

Brain Tumor Segmentation Segmentation +1

TransBTSV2: Towards Better and More Efficient Volumetric Segmentation of Medical Images

1 code implementation30 Jan 2022 Jiangyun Li, Wenxuan Wang, Chen Chen, Tianxiang Zhang, Sen Zha, Jing Wang, Hong Yu

Different from TransBTS, the proposed TransBTSV2 is not limited to brain tumor segmentation (BTS) but focuses on general medical image segmentation, providing a stronger and more efficient 3D baseline for volumetric segmentation of medical images.

Brain Tumor Segmentation Image Segmentation +3

Improving Formality Style Transfer with Context-Aware Rule Injection

no code implementations ACL 2021 Zonghai Yao, Hong Yu

Models pre-trained on large-scale regular text corpora often do not work well for user-generated data where the language styles differ significantly from the mainstream text.

Decoder Formality Style Transfer +2

CREAD: Combined Resolution of Ellipses and Anaphora in Dialogues

1 code implementation NAACL 2021 Bo-Hsiang Tseng, Shruti Bhargava, Jiarui Lu, Joel Ruben Antony Moniz, Dhivya Piraviperumal, Lin Li, Hong Yu

In this work, we propose a novel joint learning framework of modeling coreference resolution and query rewriting for complex, multi-turn dialogue understanding.

coreference-resolution Dialogue Understanding

A Dual-Questioning Attention Network for Emotion-Cause Pair Extraction with Context Awareness

1 code implementation15 Apr 2021 Qixuan Sun, Yaqi Yin, Hong Yu

Existing work follows a two-stage pipeline which identifies emotions and causes at the first step and pairs them at the second step.

Emotion Cause Extraction Emotion-Cause Pair Extraction +1

TransBTS: Multimodal Brain Tumor Segmentation Using Transformer

2 code implementations7 Mar 2021 Wenxuan Wang, Chen Chen, Meng Ding, Jiangyun Li, Hong Yu, Sen Zha

To capture the local 3D context information, the encoder first utilizes 3D CNN to extract the volumetric spatial feature maps.

Brain Tumor Segmentation Decoder +4

A prognostic dynamic model applicable to infectious diseases providing easily visualized guides -- A case study of COVID-19 in the UK

1 code implementation14 Dec 2020 Yuxuan Zhang, Chen Gong, Dawei Li, Zhi-Wei Wang, Shengda D Pu, Alex W Robertson, Hong Yu, John Parrington

A reasonable prediction of infectious diseases transmission process under different disease control strategies is an important reference point for policy makers.

Dynamic Data Selection for Curriculum Learning via Ability Estimation

no code implementations Findings of the Association for Computational Linguistics 2020 John P. Lalor, Hong Yu

Curriculum learning methods typically rely on heuristics to estimate the difficulty of training examples or the ability of the model.

Ontology-based annotation and analysis of COVID-19 phenotypes

no code implementations5 Aug 2020 Yang Wang, Fengwei Zhang, Hong Yu, Xianwei Ye, Yongqun He

The commonly occurring 17 phenotypes were classified into different groups based on the Human Phenotype Ontology (HPO).

BENTO: A Visual Platform for Building Clinical NLP Pipelines Based on CodaLab

no code implementations ACL 2020 Yonghao Jin, Fei Li, Hong Yu

In addition, the GUI interface enables researchers with limited computer background to compose tools into NLP pipelines and then apply the pipelines on their own datasets in a {``}what you see is what you get{''} (WYSIWYG) way.

Management named-entity-recognition +2

Conversational Machine Comprehension: a Literature Review

no code implementations COLING 2020 Somil Gupta, Bhanu Pratap Singh Rawat, Hong Yu

Conversational Machine Comprehension (CMC), a research track in conversational AI, expects the machine to understand an open-domain natural language text and thereafter engage in a multi-turn conversation to answer questions related to the text.

Machine Reading Comprehension Natural Language Understanding +1

Neural Data-to-Text Generation with Dynamic Content Planning

no code implementations16 Apr 2020 Kai Chen, Fayuan Li, Baotian Hu, Weihua Peng, Qingcai Chen, Hong Yu

We further design a reconstruction mechanism with a novel objective function that can reconstruct the whole entry of the used data sequentially from the hidden states of the decoder, which aids the accuracy of the generated text.

Data-to-Text Generation Decoder

Calibrating Structured Output Predictors for Natural Language Processing

no code implementations ACL 2020 Abhyuday Jagannatha, Hong Yu

Additionally, we show that our calibration method can also be used as an uncertainty-aware, entity-specific decoding step to improve the performance of the underlying model at no additional training cost or data requirements.

named-entity-recognition Named Entity Recognition +3

Continual Domain-Tuning for Pretrained Language Models

no code implementations5 Apr 2020 Subendhu Rongali, Abhyuday Jagannatha, Bhanu Pratap Singh Rawat, Hong Yu

Pre-trained language models (LM) such as BERT, DistilBERT, and RoBERTa can be tuned for different domains (domain-tuning) by continuing the pre-training phase on a new target domain corpus.

Continual Learning

ICD Coding from Clinical Text Using Multi-Filter Residual Convolutional Neural Network

3 code implementations25 Nov 2019 Fei Li, Hong Yu

The innovations of our model are two-folds: it utilizes a multi-filter convolutional layer to capture various text patterns with different lengths and a residual convolutional layer to enlarge the receptive field.

Medical Code Prediction

Bacteria Biotope Relation Extraction via Lexical Chains and Dependency Graphs

no code implementations WS 2019 Wuti Xiong, Fei Li, Ming Cheng, Hong Yu, Donghong Ji

abstract In this article, we describe our approach for the Bacteria Biotopes relation extraction (BB-rel) subtask in the BioNLP Shared Task 2019.

graph construction Relation +2

Learning Latent Parameters without Human Response Patterns: Item Response Theory with Artificial Crowds

1 code implementation IJCNLP 2019 John P. Lalor, Hao Wu, Hong Yu

We demonstrate a use-case for latent difficulty item parameters, namely training set filtering, and show that using difficulty to sample training data outperforms baseline methods.

Natural Language Inference Sentiment Analysis

HYPE: A High Performing NLP System for Automatically Detecting Hypoglycemia Events from Electronic Health Record Notes

no code implementations29 Nov 2018 Yonghao Jin, Fei Li, Hong Yu

We used this annotated dataset to train and evaluate HYPE, supervised NLP systems for hypoglycemia detection.

Language Identification with Deep Bottleneck Features

no code implementations18 Sep 2018 Zhanyu Ma, Hong Yu

In order to improve the SLD accuracy of short utterances a phase vocoder based time-scale modification(TSM) method is used to reduce and increase speech rated of the test utterance.

Language Identification Transfer Learning

Deep Neural Network for Analysis of DNA Methylation Data

no code implementations2 Aug 2018 Hong Yu, Zhanyu Ma

Many researches demonstrated that the DNA methylation, which occurs in the context of a CpG, has strong correlation with diseases, including cancer.

Histogram Transform-based Speaker Identification

no code implementations2 Aug 2018 Zhanyu Ma, Hong Yu

A novel text-independent speaker identification (SI) method is proposed.

Speaker Identification

Sentence Simplification with Memory-Augmented Neural Networks

no code implementations NAACL 2018 Tu Vu, Baotian Hu, Tsendsuren Munkhdalai, Hong Yu

Sentence simplification aims to simplify the content and structure of complex sentences, and thus make them easier to interpret for human readers, and easier to process for downstream NLP applications.

Machine Translation Sentence +2

Meta Networks

1 code implementation ICML 2017 Tsendsuren Munkhdalai, Hong Yu

Neural networks have been successfully applied in applications with a large amount of labeled data.

Continual Learning Meta-Learning

Unsupervised Ensemble Ranking of Terms in Electronic Health Record Notes Based on Their Importance to Patients

no code implementations1 Mar 2017 Jinying Chen, Hong Yu

Objective: The aim of this work was to develop FIT (Finding Important Terms for patients), an unsupervised natural language processing (NLP) system that ranks medical terms in EHR notes based on their importance to patients.

Soft Label Memorization-Generalization for Natural Language Inference

no code implementations27 Feb 2017 John P. Lalor, Hao Wu, Hong Yu

Often when multiple labels are obtained for a training example it is assumed that there is an element of noise that must be accounted for.

Memorization Natural Language Inference

DNN Filter Bank Cepstral Coefficients for Spoofing Detection

no code implementations13 Feb 2017 Hong Yu, Zheng-Hua Tan, Zhanyu Ma, Jun Guo

In order to improve the reliability of speaker verification systems, we develop a new filter bank based cepstral feature, deep neural network filter bank cepstral coefficients (DNN-FBCC), to distinguish between natural and spoofed speech.

Speaker Verification Speech Synthesis

Ranking medical jargon in electronic health record notes by adapted distant supervision

no code implementations14 Nov 2016 Jinying Chen, Abhyuday N. Jagannatha, Samah J. Jarad, Hong Yu

Methods: We developed an innovative adapted distant supervision (ADS) model based on support vector machines to rank medical jargon from EHRs.

Learning to Rank Scientific Documents from the Crowd

no code implementations4 Nov 2016 Jesse M Lingeman, Hong Yu

Finding related published articles is an important task in any science, but with the explosion of new work in the biomedical domain it has become especially challenging.

Document Ranking Learning-To-Rank +1

Neural Semantic Encoders

3 code implementations EACL 2017 Tsendsuren Munkhdalai, Hong Yu

We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders.

General Classification Machine Translation +7

Learning for Biomedical Information Extraction: Methodological Review of Recent Advances

no code implementations26 Jun 2016 Feifan Liu, Jinying Chen, Abhyuday Jagannatha, Hong Yu

Biomedical information extraction (BioIE) is important to many applications, including clinical decision support, integrative biology, and pharmacovigilance, and therefore it has been an active research.

Open Information Extraction

Bidirectional Recurrent Neural Networks for Medical Event Detection in Electronic Health Records

1 code implementation25 Jun 2016 Abhyuday Jagannatha, Hong Yu

Sequence labeling for extraction of medical events and their attributes from unstructured text in Electronic Health Record (EHR) notes is a key step towards semantic understanding of EHRs.

BIG-bench Machine Learning Event Detection

Building an Evaluation Scale using Item Response Theory

no code implementations EMNLP 2016 John P. Lalor, Hao Wu, Hong Yu

Evaluation of NLP methods requires testing against a previously vetted gold-standard test set and reporting standard metrics (accuracy/precision/recall/F1).

Natural Language Inference

Heuristic algorithms for finding distribution reducts in probabilistic rough set model

no code implementations22 Dec 2015 Xi'ao Ma, Guoyin Wang, Hong Yu

This is partly due to the fact that there are no monotonic fitness functions that are used to design heuristic attribute reduction algorithms in probabilistic rough set model.

Attribute

Cannot find the paper you are looking for? You can Submit a new open access paper.