Chinese Named entity recognition is one of the most important tasks in NLP. Two kinds of Challenges we confront are how to improve the performance in one corpus and keep its performance in another different corpus. We use a combination of statistical models, i.e. a language model to recognize person names and two CRFs models to recognize Location names and Organization names respectively. We al...

Named Entity Recognition (NER) is always limited by its lower recall resulting from the asymmetric data distribution where the NONE class dominates the entity classes. This paper presents an approach that exploits non-local information to improve the NER recall. Several kinds of non-local features encoding entity token occurrence, entity boundary and entity class are explored under Conditional ...

We here present a new method to measure the degree of protein-bound methionine sulfoxide formation at a proteome-wide scale. In human Jurkat cells that were stressed with hydrogen peroxide, over 2000 oxidation-sensitive methionines in more than 1600 different proteins were mapped and their extent of oxidation was quantified. Meta-analysis of the sequences surrounding the oxidized methionine res...

Salient region detection is important for many high-level computer vision tasks. The majority of previous works exploit element contrast to detect image saliency region. In this paper, we propose a novel approach to analyze saliency cues from multiple scales of image structure, using a multi-scale image abstraction. In each image layer global color contrast cue and color spatial distribution cu...

State-of-the-art systems of Chinese Named Entity Recognition (CNER) require large amounts of hand-crafted features and domainspecific knowledge to achieve high performance. In this paper, we apply a bidirectional LSTM-CRF neural network that utilizes both characterlevel and radical-level representations. We are the first to use characterbased BLSTM-CRF neural architecture for CNER. By contrasti...

We studied Staphylococcus aureus and Streptococcus pneumoniae carriage among elderly adults in Jakarta, Indonesia. Nasopharyngeal swabs were collected from 149 adults aged 60-97 years. Both S. aureus and S. pneumoniae were identified by conventional and molecular methods. Methicillin-resistant Staphylococcus aureus (MSRA) was determined by PCR and antibiotic susceptibility using the disk diffus...

In this paper, we introduce a novel end-end framework for multi-oriented scene text detection from an instanceaware segmentation perspective. We present Fused Text Segmentation Networks, which combine multi-level features during feature extracting as text instance may rely on finer feature expression compared to general objects. It detects and segments the text instance jointly and simultaneous...

In this paper, we present a method for object of interest detection. This method is statistical in nature and hinges in a model which combines salient features using a mixture of linear support vector machines. It exploits a divide-and-conquer strategy by partitioning the feature space into sub-regions of linearly separable data-points. This yields a structured learning approach where we learn ...

Arbitrary-oriented text detection in the wild is a very challenging task, due to the aspect ratio, scale, orientation, and illumination variations. In this paper, we propose a novel method, namely Arbitrary-oriented Text (or ArbText for short) detector, for efficient text detection in unconstrained natural scene images. Specifically, we first adopt the circle anchors rather than the rectangular...

We extended the work of Low, Ng, and Guo (2005) to create a Chinese word segmentation system based upon a maximum entropy statistical model. This system was entered into the Third International Chinese Language Processing Bakeoff and evaluated on all four corpora in their respective open tracks. Our system achieved the highest F-score for the UPUC corpus, and the second, third, and seventh high...