Zonghai Yao


2024

pdf bib
NoteChat: A Dataset of Synthetic Patient-Physician Conversations Conditioned on Clinical Notes
Junda Wang | Zonghai Yao | Zhichao Yang | Huixue Zhou | Rumeng Li | Xun Wang | Yucheng Xu | Hong Yu
Findings of the Association for Computational Linguistics ACL 2024

We introduce NoteChat, a novel cooperative multi-agent framework leveraging Large Language Models (LLMs) to generate patient-physician dialogues. NoteChat embodies the principle that an ensemble of role-specific LLMs, through structured role-play and strategic prompting, can perform their assigned roles more effectively. The synergy among these role-playing LLMs results in a cohesive and efficient dialogue generation. Evaluation on MTS-dialogue, a benchmark dataset for patient-physician dialogues-note pairs, shows that models trained with the augmented synthetic patient-physician dialogues by NoteChat outperforms other state-of-the-art models for generating clinical notes. Our comprehensive automatic and human evaluation demonstrates that NoteChat substantially surpasses state-of-the-art models like ChatGPT and GPT-4 up to 22.78% by domain experts in generating superior synthetic patient-physician dialogues based on clinical notes. NoteChat has the potential to engage patients directly and help clinical documentation, a leading cause of physician burnout.

pdf bib
LocalTweets to LocalHealth: A Mental Health Surveillance Framework Based on Twitter Data
Vijeta Deshpande | Minhwa Lee | Zonghai Yao | Zihao Zhang | Jason Brian Gibbons | Hong Yu
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Prior research on Twitter (now X) data has provided positive evidence of its utility in developing supplementary health surveillance systems. In this study, we present a new framework to surveil public health, focusing on mental health (MH) outcomes. We hypothesize that locally posted tweets are indicative of local MH outcomes and collect tweets posted from 765 neighborhoods (census block groups) in the USA. We pair these tweets from each neighborhood with the corresponding MH outcome reported by the Center for Disease Control (CDC) to create a benchmark dataset, LocalTweets. With LocalTweets, we present the first population-level evaluation task for Twitter-based MH surveillance systems. We then develop an efficient and effective method, LocalHealth, for predicting MH outcomes based on LocalTweets. When used with GPT3.5, LocalHealth achieves the highest F1-score and accuracy of 0.7429 and 79.78%, respectively, a 59% improvement in F1-score over the GPT3.5 in zero-shot setting. We also utilize LocalHealth to extrapolate CDC’s estimates to proxy unreported neighborhoods, achieving an F1-score of 0.7291. Our work suggests that Twitter data can be effectively leveraged to simulate neighborhood-level MH outcomes.

pdf bib
Do Clinicians Know How to Prompt? The Need for Automatic Prompt Optimization Help in Clinical Note Generation
Zonghai Yao | Ahmed Jaafar | Beining Wang | Zhichao Yang | Hong Yu
Proceedings of the 23rd Workshop on Biomedical Natural Language Processing

This study examines the effect of prompt engineering on the performance of Large Language Models (LLMs) in clinical note generation. We introduce an Automatic Prompt Optimization (APO) framework to refine initial prompts and compare the outputs of medical experts, non-medical experts, and APO-enhanced GPT3.5 and GPT4. Results highlight GPT4-APO’s superior performance in standardizing prompt quality across clinical note sections. A human-in-the-loop approach shows that experts maintain content quality post-APO, with a preference for their own modifications, suggesting the value of expert customization. We recommend a two-phase optimization process, leveraging APO-GPT4 for consistency and expert input for personalization.

pdf bib
UMass-BioNLP at MEDIQA-M3G 2024: DermPrompt - A Systematic Exploration of Prompt Engineering with GPT-4V for Dermatological Diagnosis
Parth Vashisht | Abhilasha Lodha | Mukta Maddipatla | Zonghai Yao | Avijit Mitra | Zhichao Yang | Sunjae Kwon | Junda Wang | Hong Yu
Proceedings of the 6th Clinical Natural Language Processing Workshop

This paper presents our team’s participation in the MEDIQA-ClinicalNLP 2024 shared task B. We present a novel approach to diagnosing clinical dermatology cases by integrating large multimodal models, specifically leveraging the capabilities of GPT-4V under a retriever and a re-ranker framework. Our investigation reveals that GPT-4V, when used as a retrieval agent, can accurately retrieve the correct skin condition 85% of the time using dermatological images and brief patient histories. Additionally, we empirically show that Naive Chain-of-Thought (CoT) works well for retrieval while Medical Guidelines Grounded CoT is required for accurate dermatological diagnosis. Further, we introduce a Multi-Agent Conversation (MAC) framework and show it’s superior performance and potential over the best CoT strategy. The experiments suggest that using naive CoT for retrieval and multi-agent conversation for critique-based diagnosis, GPT-4V can lead to an early and accurate diagnosis of dermatological conditions. The implications of this work extend to improving diagnostic workflows, supporting dermatological education, and enhancing patient care by providing a scalable, accessible, and accurate diagnostic tool.

2023

pdf bib
Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond
Haw-Shiuan Chang | Zonghai Yao | Alolika Gon | Hong Yu | Andrew McCallum
Findings of the Association for Computational Linguistics: ACL 2023

Is the output softmax layer, which is adopted by most language models (LMs), always the best way to compute the next word probability? Given so many attention layers in a modern transformer-based LM, are the pointer networks redundant nowadays? In this study, we discover that the answers to both questions are no. This is because the softmax bottleneck sometimes prevents the LMs from predicting the desired distribution and the pointer networks can be used to break the bottleneck efficiently. Based on the finding, we propose several softmax alternatives by simplifying the pointer networks and accelerating the word-by-word rerankers. In GPT-2, our proposals are significantly better and more efficient than mixture of softmax, a state-of-the-art softmax alternative. In summarization experiments, without very significantly decreasing its training/testing speed, our best method based on T5-Small improves factCC score by 2 points in CNN/DM and XSUM dataset, and improves MAUVE scores by 30% in BookSum paragraph-level dataset.

pdf bib
PaniniQA: Enhancing Patient Education Through Interactive Question Answering
Pengshan Cai | Zonghai Yao | Fei Liu | Dakuo Wang | Meghan Reilly | Huixue Zhou | Lingxi Li | Yi Cao | Alok Kapoor | Adarsha Bajracharya | Dan Berlowitz | Hong Yu
Transactions of the Association for Computational Linguistics, Volume 11

A patient portal allows discharged patients to access their personalized discharge instructions in electronic health records (EHRs). However, many patients have difficulty understanding or memorizing their discharge instructions (Zhao et al., 2017). In this paper, we present PaniniQA, a patient-centric interactive question answering system designed to help patients understand their discharge instructions. PaniniQA first identifies important clinical content from patients’ discharge instructions and then formulates patient-specific educational questions. In addition, PaniniQA is also equipped with answer verification functionality to provide timely feedback to correct patients’ misunderstandings. Our comprehensive automatic & human evaluation results demonstrate our PaniniQA is capable of improving patients’ mastery of their medical instructions through effective interactions.1

pdf bib
Improving Summarization with Human Edits
Zonghai Yao | Benjamin Schloss | Sai Selvaraj
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Recent work has shown the promise of learning with human feedback paradigms to produce human-determined high-quality text. Existing works use human feedback to train large language models (LLMs) in general domain abstractive summarization and have obtained summary quality exceeding traditional likelihood training. In this paper, we focus on a less explored form of human feedback – Human Edits. We propose Sequence Alignment (un)Likelihood Training (SALT), a novel technique to use both the human-edited and model-generated data together in the training loop. In addition, we demonstrate simulating Human Edits with ground truth summaries coming from existing training data – Imitation edits, along with the model-generated summaries obtained after the training, to reduce the need for expensive human-edit data. In our experiments, we extend human feedback exploration from general domain summarization to medical domain summarization. Our results demonstrate the effectiveness of SALT in improving the summary quality with Human and Imitation Edits. Through additional experiments, we show that SALT outperforms the conventional RLHF method (designed for human preferences) – DPO, when applied to human-edit data. We hope the evidence in our paper prompts researchers to explore, collect, and better use different human feedback approaches scalably.

pdf bib
UMASS_BioNLP at MEDIQA-Chat 2023: Can LLMs generate high-quality synthetic note-oriented doctor-patient conversations?
Junda Wang | Zonghai Yao | Avijit Mitra | Samuel Osebe | Zhichao Yang | Hong Yu
Proceedings of the 5th Clinical Natural Language Processing Workshop

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. The experiment results demonstrate that our approaches yield reasonable performance as evaluated by automatic metrics such as ROUGE, medical concept recall, BLEU, and Self-BLEU. Furthermore, we conducted a comparative analysis between our proposed method and ChatGPT and GPT-4. This analysis also investigates the potential of utilizing cooperation LLMs to generate high-quality datasets.

2022

pdf bib
MedJEx: A Medical Jargon Extraction Model with Wiki’s Hyperlink Span and Contextualized Masked Language Model Score
Sunjae Kwon | Zonghai Yao | Harmon Jordan | David Levy | Brian Corner | Hong Yu
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

This paper proposes a new natural language processing (NLP) application for identifying medical jargon terms potentially difficult for patients to comprehend from electronic health record (EHR) notes. We first present a novel and publicly available dataset with expert-annotated medical jargon terms from 18K+ EHR note sentences (MedJ). Then, we introduce a novel medical jargon extraction (MedJEx) model which has been shown to outperform existing state-of-the-art NLP models. First, MedJEx improved the overall performance when it was trained on an auxiliary Wikipedia hyperlink span dataset, where hyperlink spans provide additional Wikipedia articles to explain the spans (or terms), and then fine-tuned on the annotated MedJ data. Secondly, we found that a contextualized masked language model score was beneficial for detecting domain-specific unfamiliar jargon terms. Moreover, our results show that training on the auxiliary Wikipedia hyperlink span datasets improved six out of eight biomedical named entity recognition benchmark datasets. MedJEx is publicly available.

2021

pdf bib
Improving Formality Style Transfer with Context-Aware Rule Injection
Zonghai Yao | Hong Yu
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

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. Here we present Context-Aware Rule Injection (CARI), an innovative method for formality style transfer (FST) by injecting multiple rules into an end-to-end BERT-based encoder and decoder model. CARI is able to learn to select optimal rules based on context. The intrinsic evaluation showed that CARI achieved the new highest performance on the FST benchmark dataset. Our extrinsic evaluation showed that CARI can greatly improve the regular pre-trained models’ performance on several tweet sentiment analysis tasks. Our contributions are as follows: 1.We propose a new method, CARI, to integrate rules for pre-trained language models. CARI is context-aware and can trained end-to-end with the downstream NLP applications. 2.We have achieved new state-of-the-art results for FST on the benchmark GYAFC dataset. 3.We are the first to evaluate FST methods with extrinsic evaluation and specifically on sentiment classification tasks. We show that CARI outperformed existing rule-based FST approaches for sentiment classification.

2020

pdf bib
Zero-shot Entity Linking with Efficient Long Range Sequence Modeling
Zonghai Yao | Liangliang Cao | Huapu Pan
Findings of the Association for Computational Linguistics: EMNLP 2020

This paper considers the problem of zero-shot entity linking, in which a link in the test time may not present in training. Following the prevailing BERT-based research efforts, we find a simple yet effective way is to expand the long-range sequence modeling. Unlike many previous methods, our method does not require expensive pre-training of BERT with long position embeddings. Instead, we propose an efficient position embeddings initialization method called Embedding-repeat, which initializes larger position embeddings based on BERT-Base. On the zero-shot entity linking dataset, our method improves the STOA from 76.06% to 79.08%, and for its long data, the corresponding improvement is from 74.57% to 82.14%. Our experiments suggest the effectiveness of long-range sequence modeling without retraining the BERT model.

pdf bib
The impact of preprint servers in the formation of novel ideas
Swarup Satish | Zonghai Yao | Andrew Drozdov | Boris Veytsman
Proceedings of the First Workshop on Scholarly Document Processing

We study whether novel ideas in biomedical literature appear first in preprints or traditional journals. We develop a Bayesian method to estimate the time of appearance for a phrase in the literature, and apply it to a number of phrases, both automatically extracted and suggested by experts. We see that presently most phrases appear first in the traditional journals, but there is a number of phrases with the first appearance on preprint servers. A comparison of the general composition of texts from bioRxiv and traditional journals shows a growing trend of bioRxiv being predictive of traditional journals. We discuss the application of the method for related problems.