… We apply GAT to capture the dependency features and other embeddings to capture Chinese
Pinyin, pieces of Chinese characters, and world-level representations. We compare the …

… For the pre-trained BERT encoder, the results show that Chinese-roberta-wwm-ext is
better than Chinese-bert-base. Therefore, we will use Chinese-roberta-wwm-ext for the BERT …

… Meanwhile, we have discussed the granularity selection for Chinese word segmentation,
and select char-… We will discuss Chinese text segmentation granularity problem in this paper. …

Emerging intents may have zero or a few labeled samples in realistic dialog systems. Therefore,
models need to be capable of performing both zero-shot and few-shot intent detection. …

… The real-world dataset is built from the China interbank clearing transaction system, which
contains a total of 10k money laundering transactions and 10M normal transactions. To …

With the advance of Bitcoin technology, money laundering has been incentivised as a den
of Bitcoin blockchain, in which the user's identity is hidden behind a pseudonym known as …

Intent detection and slot filling are the two main tasks in natural language understanding
module in goal oriented conversational agents. Models which optimize these two objectives …

Convolutional neural networks (CNNs) have made great success in computer vision tasks.
But the computational complexity of CNNs is huge, which makes CNNs run slowly especially …

Face anti-spoofing technology is indispensable for the face recognition system, which is
vulnerable to malicious spoofing attacks such as printed attacks and replayed video attacks. In …

In recent years, we have become increasingly dependent on smart devices. Android is an
operating system mainly used on mobile devices, where hundreds of millions of users can …