arXiv subjects

Sheng Yu

Publications and source records attributed to Sheng Yu.

At least 37 records · Page 2Linked to original sources

arXiv2023

CoRTEx: Contrastive Learning for Representing Terms via Explanations with Applications on Constructing Biomedical Knowledge Graphs

Objective: Biomedical Knowledge Graphs play a pivotal role in various biomedical research domains. Concurrently, term clustering emerges as a crucial step in constructing these knowledge graphs, aiming to identify synonymous terms. Due to a lack of knowledge, previous contrastive learning models trained with Unified Medical Language System (UMLS) synonyms struggle at clustering difficult terms and do not generalize well beyond UMLS terms. In this work, we leverage the world knowledge from Large Language Models (LLMs) and propose Contrastive Learning for Representing Terms via Explanations (CoRTEx) to enhance term representation and significantly improves term clustering. Materials and Methods: The model training involves generating explanations for a cleaned subset of UMLS terms using ChatGPT. We employ contrastive learning, considering term and explanation embeddings simultaneously, and progressively introduce hard negative samples. Additionally, a ChatGPT-assisted BIRCH algorithm is designed for efficient clustering of a new ontology. Results: We established a clustering test set and a hard negative test set, where our model consistently achieves the highest F1 score. With CoRTEx embeddings and the modified BIRCH algorithm, we grouped 35,580,932 terms from the Biomedical Informatics Ontology System (BIOS) into 22,104,559 clusters with O(N) queries to ChatGPT. Case studies highlight the model's efficacy in handling challenging samples, aided by information from explanations. Conclusion: By aligning terms to their explanations, CoRTEx demonstrates superior accuracy over benchmark models and robustness beyond its training set, and it is suitable for clustering terms for large-scale biomedical ontologies.

cs.CL↗

arXiv2023

The Internet of Responsibilities-Connecting Human Responsibilities using Big Data and Blockchain

Accountability in the workplace is critically important and remains a challenging problem, especially with respect to workplace safety management. In this paper, we introduce a novel notion, the Internet of Responsibilities, for accountability management. Our method sorts through the list of responsibilities with respect to hazardous positions. The positions are interconnected using directed acyclic graphs (DAGs) indicating the hierarchy of responsibilities in the organization. In addition, the system detects and collects responsibilities, and represents risk areas in terms of the positions of the responsibility nodes. Finally, an automatic reminder and assignment system is used to enforce a strict responsibility control without human intervention. Using blockchain technology, we further extend our system with the capability to store, recover and encrypt responsibility data. We show that through the application of the Internet of Responsibility network model driven by Big Data, enterprise and government agencies can attain a highly secured and safe workplace. Therefore, our model offers a combination of interconnected responsibilities, accountability, monitoring, and safety which is crucial for the protection of employees and the success of organizations.

cs.CY↗

arXiv2023

A Real-Time Robust Ecological-Adaptive Cruise Control Strategy for Battery Electric Vehicles

This work addresses the ecological-adaptive cruise control problem for connected electric vehicles by a computationally efficient robust control strategy. The problem is formulated in the space-domain with a realistic description of the nonlinear electric powertrain model and motion dynamics to yield a convex optimal control problem (OCP). The OCP is approached by a novel robust model predictive control (RMPC) method handling various disturbances due to modelling mismatch and inaccurate leading vehicle information. The RMPC problem is solved by semi-definite programming relaxation and single linear matrix inequality (sLMI) techniques for further enhanced computational efficiency. The performance of the proposed real-time robust ecological-adaptive cruise control (REACC) method is evaluated using an experimentally collected driving cycle. Its robustness is verified by comparison with a nominal MPC which is shown to result in speed-limit constraint violations. The energy economy of the proposed method outperforms a state-of-the-art time-domain RMPC scheme, as a more precisely fitted convex powertrain model can be integrated into the space-domain scheme. The additional comparison with a traditional constant distance following strategy (CDFS) further verifies the effectiveness of the proposed REACC. Finally, it is verified that the REACC can be potentially implemented in real-time owing to the sLMI and resulting convex algorithm.

eess.SY↗

arXiv2023

PMC-Patients: A Large-scale Dataset of Patient Summaries and Relations for Benchmarking Retrieval-based Clinical Decision Support Systems

Objective: Retrieval-based Clinical Decision Support (ReCDS) can aid clinical workflow by providing relevant literature and similar patients for a given patient. However, the development of ReCDS systems has been severely obstructed by the lack of diverse patient collections and publicly available large-scale patient-level annotation datasets. In this paper, we aim to define and benchmark two ReCDS tasks: Patient-to-Article Retrieval (ReCDS-PAR) and Patient-to-Patient Retrieval (ReCDS-PPR) using a novel dataset called PMC-Patients. Methods: We extract patient summaries from PubMed Central articles using simple heuristics and utilize the PubMed citation graph to define patient-article relevance and patient-patient similarity. We also implement and evaluate several ReCDS systems on the PMC-Patients benchmarks, including sparse retrievers, dense retrievers, and nearest neighbor retrievers. We conduct several case studies to show the clinical utility of PMC-Patients. Results: PMC-Patients contains 167k patient summaries with 3.1M patient-article relevance annotations and 293k patient-patient similarity annotations, which is the largest-scale resource for ReCDS and also one of the largest patient collections. Human evaluation and analysis show that PMC-Patients is a diverse dataset with high-quality annotations. The evaluation of various ReCDS systems shows that the PMC-Patients benchmark is challenging and calls for further research. Conclusion: We present PMC-Patients, a large-scale, diverse, and publicly available patient summary dataset with the largest-scale patient-level relation annotations. Based on PMC-Patients, we formally define two benchmark tasks for ReCDS systems and evaluate various existing retrieval methods. PMC-Patients can largely facilitate methodology research on ReCDS systems and shows real-world clinical utility.

cs.CL↗

arXiv2022

A Computationally Efficient Robust Model Predictive Control Framework for Ecological Adaptive Cruise Control Strategy of Electric Vehicles

The recent advancement in vehicular networking technology provides novel solutions for designing intelligent and sustainable vehicle motion controllers. This work addresses a car-following task, where the feedback linearisation method is combined with a robust model predictive control (RMPC) scheme to safely, optimally and efficiently control a connected electric vehicle. In particular, the nonlinear dynamics are linearised through a feedback linearisation method to maintain an efficient computational speed and to guarantee global optimality. At the same time, the inevitable model mismatch is dealt with by the RMPC design. The control objective of the RMPC is to optimise the electric energy efficiency of the ego vehicle with consideration of a bounded model mismatch disturbance subject to satisfaction of physical and safety constraints. Numerical results first verify the validity and robustness through a comparison between the proposed RMPC and a nominal MPC. Further investigation into the performance of the proposed method reveals a higher energy efficiency and passenger comfort level as compared to a recently proposed benchmark method using the space-domain modelling approach.

eess.SY↗

arXiv2022

Multimodal Learning on Graphs for Disease Relation Extraction

Objective: Disease knowledge graphs are a way to connect, organize, and access disparate information about diseases with numerous benefits for artificial intelligence (AI). To create knowledge graphs, it is necessary to extract knowledge from multimodal datasets in the form of relationships between disease concepts and normalize both concepts and relationship types. Methods: We introduce REMAP, a multimodal approach for disease relation extraction and classification. The REMAP machine learning approach jointly embeds a partial, incomplete knowledge graph and a medical language dataset into a compact latent vector space, followed by aligning the multimodal embeddings for optimal disease relation extraction. Results: We apply REMAP approach to a disease knowledge graph with 96,913 relations and a text dataset of 1.24 million sentences. On a dataset annotated by human experts, REMAP improves text-based disease relation extraction by 10.0% (accuracy) and 17.2% (F1-score) by fusing disease knowledge graphs with text information. Further, REMAP leverages text information to recommend new relationships in the knowledge graph, outperforming graph-based methods by 8.4% (accuracy) and 10.4% (F1-score). Conclusion: REMAP is a multimodal approach for extracting and classifying disease relationships by fusing structured knowledge and text information. REMAP provides a flexible neural architecture to easily find, access, and validate AI-driven relationships between disease concepts.

cs.LG↗

arXiv2022

Semi-constraint Optimal Transport for Entity Alignment with Dangling Cases

Entity alignment (EA) merges knowledge graphs (KGs) by identifying the equivalent entities in different graphs, which can effectively enrich knowledge representations of KGs. However, in practice, different KGs often include dangling entities whose counterparts cannot be found in the other graph, which limits the performance of EA methods. To improve EA with dangling entities, we propose an unsupervised method called Semi-constraint Optimal Transport for Entity Alignment in Dangling cases (SoTead). Our main idea is to model the entity alignment between two KGs as an optimal transport problem from one KG's entities to the others. First, we set pseudo entity pairs between KGs based on pretrained word embeddings. Then, we conduct contrastive metric learning to obtain the transport cost between each entity pair. Finally, we introduce a virtual entity for each KG to "align" the dangling entities from the other KGs, which relaxes the optimization constraints and leads to a semi-constraint optimal transport. In the experimental part, we first show the superiority of SoTead on a commonly-used entity alignment dataset. Besides, to analyze the ability for dangling entity detection with other baselines, we construct a medical cross-lingual knowledge graph dataset, MedED, where our SoTead also reaches state-of-the-art performance.

cs.CL↗

arXiv2022

Efficient Symptom Inquiring and Diagnosis via Adaptive Alignment of Reinforcement Learning and Classification

Medical automatic diagnosis aims to imitate human doctors in real-world diagnostic processes and to achieve accurate diagnoses by interacting with the patients. The task is formulated as a sequential decision-making problem with a series of symptom inquiring steps and the final diagnosis. Recent research has studied incorporating reinforcement learning for symptom inquiring and classification techniques for disease diagnosis, respectively. However, studies on efficiently and effectively combining the two procedures are still lacking. To address this issue, we devise an adaptive mechanism to align reinforcement learning and classification methods using distribution entropy as the medium. Additionally, we created a new dataset for patient simulation to address the lacking of large-scale evaluation benchmarks. The dataset is extracted from the MedlinePlus knowledge base and contains significantly more diseases and more comprehensive symptoms and examination information than existing datasets. Experimental evaluation shows that our method outperforms three current state-of-the-art methods on different datasets by achieving higher medical diagnosis accuracy with fewer inquiring turns.

cs.LG↗

arXiv2022

Generative Biomedical Entity Linking via Knowledge Base-Guided Pre-training and Synonyms-Aware Fine-tuning

Entities lie in the heart of biomedical natural language understanding, and the biomedical entity linking (EL) task remains challenging due to the fine-grained and diversiform concept names. Generative methods achieve remarkable performances in general domain EL with less memory usage while requiring expensive pre-training. Previous biomedical EL methods leverage synonyms from knowledge bases (KB) which is not trivial to inject into a generative method. In this work, we use a generative approach to model biomedical EL and propose to inject synonyms knowledge in it. We propose KB-guided pre-training by constructing synthetic samples with synonyms and definitions from KB and require the model to recover concept names. We also propose synonyms-aware fine-tuning to select concept names for training, and propose decoder prompt and multi-synonyms constrained prefix tree for inference. Our method achieves state-of-the-art results on several biomedical EL tasks without candidate selection which displays the effectiveness of proposed pre-training and fine-tuning strategies.

cs.CL↗

arXiv2022

BIOS: An Algorithmically Generated Biomedical Knowledge Graph

Biomedical knowledge graphs (BioMedKGs) are essential infrastructures for biomedical and healthcare big data and artificial intelligence (AI), facilitating natural language processing, model development, and data exchange. For decades, these knowledge graphs have been developed via expert curation; however, this method can no longer keep up with today's AI development, and a transition to algorithmically generated BioMedKGs is necessary. In this work, we introduce the Biomedical Informatics Ontology System (BIOS), the first large-scale publicly available BioMedKG generated completely by machine learning algorithms. BIOS currently contains 4.1 million concepts, 7.4 million terms in two languages, and 7.3 million relation triplets. We present the methodology for developing BIOS, including the curation of raw biomedical terms, computational identification of synonymous terms and aggregation of these terms to create concept nodes, semantic type classification of the concepts, relation identification, and biomedical machine translation. We provide statistics on the current BIOS content and perform preliminary assessments of term quality, synonym grouping, and relation extraction. The results suggest that machine learning-based BioMedKG development is a viable alternative to traditional expert curation.

cs.CL↗

arXiv2022

BioBART: Pretraining and Evaluation of A Biomedical Generative Language Model

Pretrained language models have served as important backbones for natural language processing. Recently, in-domain pretraining has been shown to benefit various domain-specific downstream tasks. In the biomedical domain, natural language generation (NLG) tasks are of critical importance, while understudied. Approaching natural language understanding (NLU) tasks as NLG achieves satisfying performance in the general domain through constrained language generation or language prompting. We emphasize the lack of in-domain generative language models and the unsystematic generative downstream benchmarks in the biomedical domain, hindering the development of the research community. In this work, we introduce the generative language model BioBART that adapts BART to the biomedical domain. We collate various biomedical language generation tasks including dialogue, summarization, entity linking, and named entity recognition. BioBART pretrained on PubMed abstracts has enhanced performance compared to BART and set strong baselines on several tasks. Furthermore, we conduct ablation studies on the pretraining tasks for BioBART and find that sentence permutation has negative effects on downstream tasks.

cs.CL↗

arXiv2022

Automatic Biomedical Term Clustering by Learning Fine-grained Term Representations

Term clustering is important in biomedical knowledge graph construction. Using similarities between terms embedding is helpful for term clustering. State-of-the-art term embeddings leverage pretrained language models to encode terms, and use synonyms and relation knowledge from knowledge graphs to guide contrastive learning. These embeddings provide close embeddings for terms belonging to the same concept. However, from our probing experiments, these embeddings are not sensitive to minor textual differences which leads to failure for biomedical term clustering. To alleviate this problem, we adjust the sampling strategy in pretraining term embeddings by providing dynamic hard positive and negative samples during contrastive learning to learn fine-grained representations which result in better biomedical term clustering. We name our proposed method as CODER++, and it has been applied in clustering biomedical concepts in the newly released Biomedical Knowledge Graph named BIOS.

cs.CL↗

arXiv2022

An Accurate Unsupervised Method for Joint Entity Alignment and Dangling Entity Detection

Knowledge graph integration typically suffers from the widely existing dangling entities that cannot find alignment cross knowledge graphs (KGs). The dangling entity set is unavailable in most real-world scenarios, and manually mining the entity pairs that consist of entities with the same meaning is labor-consuming. In this paper, we propose a novel accurate Unsupervised method for joint Entity alignment (EA) and Dangling entity detection (DED), called UED. The UED mines the literal semantic information to generate pseudo entity pairs and globally guided alignment information for EA and then utilizes the EA results to assist the DED. We construct a medical cross-lingual knowledge graph dataset, MedED, providing data for both the EA and DED tasks. Extensive experiments demonstrate that in the EA task, UED achieves EA results comparable to those of state-of-the-art supervised EA baselines and outperforms the current state-of-the-art EA methods by combining supervised EA data. For the DED task, UED obtains high-quality results without supervision.

cs.CL↗

arXiv2022

Sentence Alignment with Parallel Documents Facilitates Biomedical Machine Translation

Objective: Today's neural machine translation (NMT) can achieve near human-level translation quality and greatly facilitates international communications, but the lack of parallel corpora poses a key problem to the development of translation systems for highly specialized domains, such as biomedicine. This work presents an unsupervised algorithm for deriving parallel corpora from document-level translations by using sentence alignment and explores how training materials affect the performance of biomedical NMT systems. Materials and Methods: Document-level translations are mixed to train bilingual word embeddings (BWEs) for the evaluation of cross-lingual word similarity, and sentence distance is defined by combining semantic and positional similarities of the sentences. The alignment of sentences is formulated as an extended earth mover's distance problem. A Chinese-English biomedical parallel corpus is derived with the proposed algorithm using bilingual articles from UpToDate and translations of PubMed abstracts, which is then used for the training and evaluation of NMT. Results: On two manually aligned translation datasets, the proposed algorithm achieved accurate sentence alignment in the 1-to-1 cases and outperformed competing algorithms in the many-to-many cases. The NMT model fine-tuned on biomedical data significantly improved the in-domain translation quality (zh-en: +17.72 BLEU; en-zh: +17.02 BLEU). Both the size of the training data and the combination of different corpora can significantly affect the model's performance. Conclusion: The proposed algorithm relaxes the assumption for sentence alignment and effectively generates accurate translation pairs that facilitate training high quality biomedical NMT models.

cs.CL↗

arXiv2022

SpinQ Triangulum: a commercial three-qubit desktop quantum computer

SpinQ Triangulum is the second generation of the desktop quantum computers designed and manufactured by SpinQ Technology. SpinQ's desktop quantum computer series, based on room temperature NMR spectrometer, provide light-weighted, cost-effective and maintenance-free quantum computing platforms that aim to provide real-device experience for quantum computing education for K-12 and college level. These platforms also feature quantum control design capabilities for studying quantum control and quantum noise. Compared with the first generation product, the two-qubit SpinQ Gemini, Triangulum features a three-qubit QPU, smaller dimensions (61 * 33 * 56 cm^3) and lighter (40 kg). Furthermore, the magnetic field is more stable and the performance of quantum control is more accurate. This paper introduces the system design of Triangulum and its new features. As an example of performing quantum computing tasks, we present the implementation of the Harrow-Hassidim-Lloyd (HHL) algorithm on Triangulum, demonstrating Triangulum's capability of undertaking complex quantum computing tasks. SpinQ will continue to develop desktop quantum computing platform with more qubits. Meanwhile, a simplified version of SpinQ Gemini, namely Gemini Mini (https://www.spinq.cn/products#geminiMini-anchor) , has been recently realised. Gemini Mini is much more portable (20* 35 * 26 cm^3, 14 kg) and affordable for most K-12 schools around the world.

quant-ph↗

arXiv2021

Biomedical Question Answering: A Survey of Approaches and Challenges

Automatic Question Answering (QA) has been successfully applied in various domains such as search engines and chatbots. Biomedical QA (BQA), as an emerging QA task, enables innovative applications to effectively perceive, access and understand complex biomedical knowledge. There have been tremendous developments of BQA in the past two decades, which we classify into 5 distinctive approaches: classic, information retrieval, machine reading comprehension, knowledge base and question entailment approaches. In this survey, we introduce available datasets and representative methods of each BQA approach in detail. Despite the developments, BQA systems are still immature and rarely used in real-life settings. We identify and characterize several key challenges in BQA that might lead to this issue, and discuss some potential future directions to explore.

cs.CL↗

arXiv2021

CODER: Knowledge infused cross-lingual medical term embedding for term normalization

This paper proposes CODER: contrastive learning on knowledge graphs for cross-lingual medical term representation. CODER is designed for medical term normalization by providing close vector representations for different terms that represent the same or similar medical concepts with cross-lingual support. We train CODER via contrastive learning on a medical knowledge graph (KG) named the Unified Medical Language System, where similarities are calculated utilizing both terms and relation triplets from KG. Training with relations injects medical knowledge into embeddings and aims to provide potentially better machine learning features. We evaluate CODER in zero-shot term normalization, semantic similarity, and relation classification benchmarks, which show that CODERoutperforms various state-of-the-art biomedical word embedding, concept embeddings, and contextual embeddings. Our codes and models are available at https://github.com/GanjinZero/CODER.

cs.CL↗

arXiv2021

SpinQ Gemini: a desktop quantum computer for education and research

SpinQ Gemini is a commercial desktop quantum computer designed and manufactured by SpinQ Technology. It is an integrated hardware-software system. The first generation product with two qubits was launched in January 2020. The hardware is based on NMR spectrometer, with permanent magnets providing $\sim 1$ T magnetic field. SpinQ Gemini operates under room temperature ($0$-$30^{\circ}$C), highlighting its lightweight (55 kg with a volume of $70\times 40 \times 80$ cm$^3$), cost-effective (under $50$k USD), and maintenance-free. SpinQ Gemini aims to provide real-device experience for quantum computing education for K-12 and at the college level. It also features quantum control design capabilities that benefit the researchers studying quantum control and quantum noise. Since its first launch, SpinQ Gemini has been shipped to institutions in Canada, Taiwan and Mainland China. This paper introduces the system of design of SpinQ Gemini, from hardware to software. We also demonstrate examples for performing quantum computing tasks on SpinQ Gemini, including one task for a variational quantum eigensolver of a two-qubit Heisenberg model. The next generations of SpinQ quantum computing devices will adopt models of more qubits, advanced control functions for researchers with comparable cost, as well as simplified models for much lower cost (under $5$k USD) for K-12 education. We believe that low-cost portable quantum computer products will facilitate hands-on experience for teaching quantum computing at all levels, well-prepare younger generations of students and researchers for the future of quantum technologies.

quant-ph↗