arXiv subjects

Yangming Zhou

Publications and source records attributed to Yangming Zhou.

29 records · Page 2Linked to original sources

arXiv2019

Enriching Medcial Terminology Knowledge Bases via Pre-trained Language Model and Graph Convolutional Network

Enriching existing medical terminology knowledge bases (KBs) is an important and never-ending work for clinical research because new terminology alias may be continually added and standard terminologies may be newly renamed. In this paper, we propose a novel automatic terminology enriching approach to supplement a set of terminologies to KBs. Specifically, terminology and entity characters are first fed into pre-trained language model to obtain semantic embedding. The pre-trained model is used again to initialize the terminology and entity representations, then they are further embedded through graph convolutional network to gain structure embedding. Afterwards, both semantic and structure embeddings are combined to measure the relevancy between the terminology and the entity. Finally, the optimal alignment is achieved based on the order of relevancy between the terminology and all the entities in the KB. Experimental results on clinical indicator terminology KB, collected from 38 top-class hospitals of Shanghai Hospital Development Center, show that our proposed approach outperforms baseline methods and can effectively enrich the KB.

cs.CL↗

arXiv2018

PatientEG Dataset: Bringing Event Graph Model with Temporal Relations to Electronic Medical Records

Medical activities, such as diagnoses, medicine treatments, and laboratory tests, as well as temporal relations between these activities are the basic concepts in clinical research. However, existing relational data model on electronic medical records (EMRs) lacks explicit and accurate semantic definitions of these concepts. It leads to the inconvenience of query construction and the inefficiency of query execution where multi-table join queries are frequently required. In this paper, we propose a patient event graph (PatientEG) model to capture the characteristics of EMRs. We respectively define five types of medical entities, five types of medical events and five types of temporal relations. Based on the proposed model, we also construct a PatientEG dataset with 191,294 events, 3,429 distinct entities, and 545,993 temporal relations using EMRs from Shanghai Shuguang hospital. To help to normalize entity values which contain synonyms, hyponymies, and abbreviations, we link them with the Chinese biomedical knowledge graph. With the help of PatientEG dataset, we are able to conveniently perform complex queries for clinical research such as auxiliary diagnosis and therapeutic effectiveness analysis. In addition, we provide a SPARQL endpoint to access PatientEG dataset and the dataset is also publicly available online. Also, we list several illustrative SPARQL queries on our website.

cs.CY↗

arXiv2018

An attention-based Bi-GRU-CapsNet model for hypernymy detection between compound entities

Named entities are usually composable and extensible. Typical examples are names of symptoms and diseases in medical areas. To distinguish these entities from general entities, we name them \textit{compound entities}. In this paper, we present an attention-based Bi-GRU-CapsNet model to detect hypernymy relationship between compound entities. Our model consists of several important components. To avoid the out-of-vocabulary problem, English words or Chinese characters in compound entities are fed into the bidirectional gated recurrent units. An attention mechanism is designed to focus on the differences between the two compound entities. Since there are some different cases in hypernymy relationship between compound entities, capsule network is finally employed to decide whether the hypernymy relationship exists or not. Experimental results demonstrate

cs.CL↗

arXiv2018

Automatic Severity Classification of Coronary Artery Disease via Recurrent Capsule Network

Coronary artery disease (CAD) is one of the leading causes of cardiovascular disease deaths. CAD condition progresses rapidly, if not diagnosed and treated at an early stage may eventually lead to an irreversible state of the heart muscle death. Invasive coronary arteriography is the gold standard technique for CAD diagnosis. Coronary arteriography texts describe which part has stenosis and how much stenosis is in details. It is crucial to conduct the severity classification of CAD. In this paper, we employ a recurrent capsule network (RCN) to extract semantic relations between clinical named entities in Chinese coronary arteriography texts, through which we can automatically find out the maximal stenosis for each lumen to inference how severe CAD is according to the improved method of Gensini. Experimental results on the corpus collected from Shanghai Shuguang Hospital show that our proposed method achieves an accuracy of 97.0\% in the severity classification of CAD.

cs.CL↗

arXiv2018

Fast and Accurate Recognition of Chinese Clinical Named Entities with Residual Dilated Convolutions

Clinical Named Entity Recognition (CNER) aims to identify and classify clinical terms such as diseases, symptoms, treatments, exams, and body parts in electronic health records, which is a fundamental and crucial task for clinical and translation research. In recent years, deep learning methods have achieved significant success in CNER tasks. However, these methods depend greatly on Recurrent Neural Networks (RNNs), which maintain a vector of hidden activations that are propagated through time, thus causing too much time to train models. In this paper, we propose a Residual Dilated Convolutional Neural Network with Conditional Random Field (RD-CNN-CRF) to solve it. Specifically, Chinese characters and dictionary features are first projected into dense vector representations, then they are fed into the residual dilated convolutional neural network to capture contextual features. Finally, a conditional random field is employed to capture dependencies between neighboring tags. Computational results on the CCKS-2017 Task 2 benchmark dataset show that our proposed RD-CNN-CRF method competes favorably with state-of-the-art RNN-based methods both in terms of computational performance and training time.

cs.CL↗

arXiv2018

Random Forest for Label Ranking

Label ranking aims to learn a mapping from instances to rankings over a finite number of predefined labels. Random forest is a powerful and one of the most successful general-purpose machine learning algorithms of modern times. In this paper, we present a powerful random forest label ranking method which uses random decision trees to retrieve nearest neighbors. We have developed a novel two-step rank aggregation strategy to effectively aggregate neighboring rankings discovered by the random forest into a final predicted ranking. Compared with existing methods, the new random forest method has many advantages including its intrinsically scalable tree data structure, highly parallel-able computational architecture and much superior performance. We present extensive experimental results to demonstrate that our new method achieves the highly competitive performance compared with state-of-the-art methods for datasets with complete ranking and datasets with only partial ranking information.

cs.LG↗

arXiv2018

Incorporating Dictionaries into Deep Neural Networks for the Chinese Clinical Named Entity Recognition

Clinical Named Entity Recognition (CNER) aims to identify and classify clinical terms such as diseases, symptoms, treatments, exams, and body parts in electronic health records, which is a fundamental and crucial task for clinical and translational research. In recent years, deep neural networks have achieved significant success in named entity recognition and many other Natural Language Processing (NLP) tasks. Most of these algorithms are trained end to end, and can automatically learn features from large scale labeled datasets. However, these data-driven methods typically lack the capability of processing rare or unseen entities. Previous statistical methods and feature engineering practice have demonstrated that human knowledge can provide valuable information for handling rare and unseen cases. In this paper, we address the problem by incorporating dictionaries into deep neural networks for the Chinese CNER task. Two different architectures that extend the Bi-directional Long Short-Term Memory (Bi-LSTM) neural network and five different feature representation schemes are proposed to handle the task. Computational results on the CCKS-2017 Task 2 benchmark dataset show that the proposed method achieves the highly competitive performance compared with the state-of-the-art deep learning methods.

cs.CL↗

arXiv2017

Memetic search for identifying critical nodes in sparse graphs

Critical node problems involve identifying a subset of critical nodes from an undirected graph whose removal results in optimizing a pre-defined measure over the residual graph. As useful models for a variety of practical applications, these problems are computational challenging. In this paper, we study the classic critical node problem (CNP) and introduce an effective memetic algorithm for solving CNP. The proposed algorithm combines a double backbone-based crossover operator (to generate promising offspring solutions), a component-based neighborhood search procedure (to find high-quality local optima) and a rank-based pool updating strategy (to guarantee a healthy population). Specially, the component-based neighborhood search integrates two key techniques, i.e., two-phase node exchange strategy and node weighting scheme. The double backbone-based crossover extends the idea of general backbone-based crossovers. Extensive evaluations on 42 synthetic and real-world benchmark instances show that the proposed algorithm discovers 21 new upper bounds and matches 18 previous best-known upper bounds. We also demonstrate the relevance of our algorithm for effectively solving a variant of the classic CNP, called the cardinality-constrained critical node problem. Finally, we investigate the usefulness of each key algorithmic component.

cs.AI↗

arXiv2017

When data mining meets optimization: A case study on the quadratic assignment problem

This paper presents a hybrid approach called frequent pattern based search that combines data mining and optimization. The proposed method uses a data mining procedure to mine frequent patterns from a set of high-quality solutions collected from previous search, and the mined frequent patterns are then employed to build starting solutions that are improved by an optimization procedure. After presenting the general approach and its composing ingredients, we illustrate its application to solve the well-known and challenging quadratic assignment problem. Computational results on the 21 hardest benchmark instances show that the proposed approach competes favorably with state-of-the-art algorithms both in terms of solution quality and computing time.

cs.DM↗

arXiv2016

An iterated local search algorithm for the minimum differential dispersion problem

Given a set of $n$ elements separated by a pairwise distance matrix, the minimum differential dispersion problem (Min-Diff DP) aims to identify a subset of m elements (m < n) such that the difference between the maximum sum and the minimum sum of the inter-element distances between any two chosen elements is minimized. We propose an effective iterated local search (denoted by ILS_MinDiff) for Min-Diff DP. To ensure an effective exploration and exploitation of the search space, the proposed ILS_MinDiff algorithm iterates through three sequential search phases: a fast descent-based neighborhood search phase to find a local optimum from a given starting solution, a local optima exploring phase to visit nearby high-quality solutions around a given local optimum, and a local optima escaping phase to move away from the current search region. Experimental results on six data sets of 190 benchmark instances demonstrate that ILS_MinDiff competes favorably with the state-of-the-art algorithms by finding 130 improved best results (new upper bounds).

cs.DM↗

arXiv2016

Reinforcement learning based local search for grouping problems: A case study on graph coloring

Grouping problems aim to partition a set of items into multiple mutually disjoint subsets according to some specific criterion and constraints. Grouping problems cover a large class of important combinatorial optimization problems that are generally computationally difficult. In this paper, we propose a general solution approach for grouping problems, i.e., reinforcement learning based local search (RLS), which combines reinforcement learning techniques with descent-based local search. The viability of the proposed approach is verified on a well-known representative grouping problem (graph coloring) where a very simple descent-based coloring algorithm is applied. Experimental studies on popular DIMACS and COLOR02 benchmark graphs indicate that RLS achieves competitive performances compared to a number of well-known coloring algorithms.

cs.AI↗