Cross-domain learning text classification aims to train an accurate model for a target domain by using labeled text data from a source domain with different but related data distributions. To narrow the data distribution gap between different domains, most of the previous approaches utilize the bag-of-words model to obtain latent features representation of the text. However, this kind of model loses the word order information and misses the background knowledge of the text. As the result, the conceptual information of the text is ignored to a big extent. In this paper, we propose a novel framework named Document Concept Vector for the cross-domain text classification which leverages both the neural network and the knowledge base in order to produce a high quality representation of the text. Specifically, a raw document is first transformed into a conceptualized document which consists of a set of concepts by utilizing a large taxonomy knowledge base. After that, the conceptualized document is transformed into a document vector through the neural network and the vector is used as the concept level feature of the original document. Finally, we conducted the experiments on two real-world corpora and compared it with both traditional classification algorithms and several state-of-the-art approaches of cross-domain text classification. The results validate the effectiveness of our framework.

The invention discloses a topic model based medical record classification method, which comprises the steps of 1) extracting single medical records from medical record books through OCR and text structured processing; 2) performing preprocessing on all structured single medical records by using a Chinese word segmentation tool, wherein the preprocessing comprises word segmentation and top word removing; 3) filtering word segmentation results of the medical records by respectively using domain dictionaries for traditional Chinese medicines, prescriptions, diseases, symptoms, syndromes and treatment methods, and acquiring six word lists corresponding to each medical record; 4) building a medical record topic model containing the following seven categories: common words, traditional Chinese medicines, prescriptions, diseases, symptoms, syndromes and treatment methods; 5) inputting the six word lists, which are acquired by filtering in the step 3), of each medical record and words left in the medical records into the topic model to train, and acquiring document topic distribution through Gibbs sampling; and 6) inputting the document topic distribution into a trained SVM classifier so as to acquire corresponding categories.

Text classification is one of the fundamental tasks in text mining. In the medical domain, there have been a number of studies on text classification in modern medicine clinical notes written in English. However, very limited text classification research has been conducted on clinical notes written in Chinese, especially traditional Chinese medicine (TCM) clinical records. The goal of this study was to investigate features and machine learning classification algorithms for TCM clinical text classification. We collected 7,037 TCM clinical records of famous TCM doctors as our dataset, and investigated the effects of different types of features and classification algorithms. Additionally, we proposed a novel method to combine deep learning text representation with TCM domain knowledge, which results in the best classification performance.

In Traditional Chinese Medicine(TCM) area, medical records are the objective record of a doctor's diagnosis and treatment and they are the basis of the TCM development. However, existing medical records of TCM are derived from books, medical cases, Web and most of them lack the categories information. In this paper, we propose a text classification method for the TCM medical record based on cross -domain topic model. First, we transform the physical books into the digital documents, then tokenize and filter the documents with domain lexicons to achieve the significative sequences of words which largely maintain the topics of original documents. Second, we use the cross domain topic model named Topic Relevance Weighting Model(TRWM) to generate the features. Finally, the generated features are leveraged for the medical records classification and compared with the baselines. The experimental results validate the effectiveness of our method.

跨领域分类的目的在于通过对有标签的源邻域的数据集进行训练建立以模型然后再将该模型应用于对一个数据分布相关但不同的目标领域的数据集进行分类。为了削减不同领域数据集之间分布的差异,很多之前的工作利用词袋模型来获得隐性的特征以表达文本。然而这类模型都只关注于词之间的表面联系并未考虑词的顺序和词的语义信息。在本文中,我们通过提出利用文本向量的方式对跨领域分类的文本进行语义层次建模。通过神经网络将任意长度原始文本重新表示为一个定长的向量,克服了词袋模型的缺陷。我们同时对两个现实世界的数据集进行了实验,包括二分类和多分类实验,并且和传统的分类算法以及顶尖的跨领域分类方法进行了对比。实验结果说明了我们方法的有效性。