Towards easier and faster sequence labeling for natural language processing: A search-based probabilistic online learning framework (SAPO)

Improving Loanword Identification in Low-Resource Language with Data Augmentation and Multiple Feature Fusion

Loanword identification is studied in recent years to alleviate data sparseness in several natural language processing (NLP) tasks, such as machine translation, cross-lingual information retrieval, and so on. However, recent studies on this topic usually put efforts on high-resource languages (such as Chinese, English, and Russian); for low-resource languages, such as Uyghur and Mongolian, due to the limitation of resources and lack of annotated data, loanword identification on these languages tends to have lower performance. To overcome this problem, we first propose a lexical constraint-based data augmentation method to generate training data for low-resource language loanword identification; then, a loanword identification model based on a log-linear RNN is introduced to improve the performance of low-resource loanword identification by incorporating features such as word-level embeddings, character-level embeddings, pronunciation similarity, and part-of-speech (POS) into one model. Experimental results on loanword identification in Uyghur (in this study, we mainly focus on Arabic, Chinese, Russian, and Turkish loanwords in Uyghur) showed that our proposed method achieves best performance compared with several strong baseline systems.

Automatic construction of academic profile: A case of information science domain

To provide junior researchers with domain-specific concepts efficiently, an automatic approach for academic profiling is needed. First, to obtain personal records of a given scholar, typical supervised approaches often utilise structured data like infobox in Wikipedia as training dataset, but it may lead to a severe mis-labelling problem when they are utilised to train a model directly. To address this problem, a new relation embedding method is proposed for fine-grained entity typing, in which the initial vector of entities and a new penalty scheme are considered, based on the semantic distance of entities and relations. Also, to highlight critical concepts relevant to renowned scholars, scholars’ selective bibliographies which contain massive academic terms are analysed by a newly proposed extraction method based on logistic regression, AdaBoost algorithm and learning-to-rank techniques. It bridges the gap that conventional supervised methods only return binary classification results and fail to help researchers understand the relative importance of selected concepts. Categories of experiments on academic profiling and corresponding benchmark datasets demonstrate that proposed approaches outperform existing methods notably. The proposed techniques provide an automatic way for junior researchers to obtain organised knowledge in a specific domain, including scholars’ background information and domain-specific concepts.

Preserving differential privacy in deep neural networks with relevance-based adaptive noise imposition

In recent years, deep learning achieves remarkable results in the field of artificial intelligence. However, the training process of deep neural networks may cause the leakage of individual privacy. Given the model and some background information of the target individual, the adversary can maliciously infer the sensitive feature of the target individual. Therefore, it is imperative to preserve the sensitive information in the training data. Differential privacy is a state-of-the-art paradigm for providing the privacy guarantee of datasets, which protects the private and sensitive information from the attack of adversaries significantly. However, the existing privacy-preserving models based on differential privacy are less than satisfactory since traditional approaches always inject the same amount of noise into parameters to preserve the sensitive information, which may impact the trade-off between the model utility and the privacy guarantee of training data. In this paper, we present a general differentially private deep neural networks learning framework based on relevance analysis, which aims to bridge the gap between private and non-private models while providing an effective privacy guarantee of sensitive information. The proposed model perturbs gradients according to the relevance between neurons in different layers and the model output. Specifically, during the process of backward propagation, more noise is added to gradients of neurons that have less relevance to the model output, and vice-versa. Experiments on five real datasets demonstrate that our mechanism not only bridges the gap between private and non-private models, but also prevents the disclosure of sensitive information effectively.