Abstract Standard multi-task benchmarks are essential for developing pretraining models that can generalize to various downstream tasks. Existing natural language processing (NLP) usually focus only on understanding or generating short texts. However, long text modeling requires many distinct abilities in contrast texts, such as the of long-range discourse and commonsense relations, coherence c...

Text Classification is an important research area in natural language processing (NLP) that has received a considerable amount of scholarly attention recent years. However, real Chinese online news characterized by long text, large information and complex structure, which also reduces the accuracy text classification as result. To improve news, we propose BERT-based local feature convolutional ...

Characters have commonly been regarded as the minimal processing unit in Natural Language Processing (NLP). But many non-latin languages have hieroglyphic writing systems, involving a big alphabet with thousands or millions of characters. Each character is composed of even smaller parts, which are often ignored by the previous work. In this paper, we propose a novel architecture employing two s...

text classification is an important research field in information retrieval and text mining. the main task in text classification is to assign text documents in predefined categories based on documents’ contents and labeled-training samples. since word detection is a difficult and time consuming task in persian language, bayesian text classifier is an appropriate approach to deal with different...

We examine approaches of statistical machine translation without parallel data (SMT). SMT has achieved impressive performance by leveraging large amounts of parallel data in the source and target languages. But such data is available only for a few language pairs and domains. Using human annotation to create new parallel corpora sufficient for building a good translation system is too expensive...

Neural word segmentation has attracted more and more research interests for its ability to alleviate the effort of feature engineering and utilize the external resource by the pre-trained character or word embeddings. In this paper, we propose a new neural model to incorporate the wordlevel information for Chinese word segmentation. Unlike the previous wordbased models, our model still adopts t...

Automatic query expansion methods for English text retrieval have been studied for a long time, with debatable success in many instances. In this paper, we study what the retrieval eeectiveness will be achieved when we apply a successful automatic query expansion method for English text retrieval to Japanese text retrieval. Our experiments show that the automatic query expansion method also res...

A novel keystroke biometric system for long-text input was developed and evaluated for user identification and authentication applications. The system consists of a Java applet to collect raw keystroke data over the internet, a feature extractor, and pattern classifiers to make identification or authentication decisions. Experiments on over 100 subjects investigated two input modes – copy and f...

the length of the testing text. In summary, we found the keystroke biometric effective for identifying up to 30 users inputting text under the following conditions: sufficient training and testing text length, sufficient number of enrollment samples, and same keyboard type used for enrollment and testing.