[HTML][HTML] Multi-level semantic fusion network for Chinese medical named entity recognition
J Shi, M Sun, Z Sun, M Li, Y Gu, W Zhang - Journal of Biomedical …, 2022 - Elsevier
… 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 …
Pinyin, pieces of Chinese characters, and world-level representations. We compare the …
Few-shot nlu with vector projection distance and abstract triangular crf
… 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 …
better than Chinese-bert-base. Therefore, we will use Chinese-roberta-wwm-ext for the BERT …
A short text classification approach with event detection and conceptual information
W Yin, L Shen - Proceedings of the 2020 5th International Conference …, 2020 - dl.acm.org
… 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. …
and select char-… We will discuss Chinese text segmentation granularity problem in this paper. …
Episode-Based Prompt Learning for Any-Shot Intent Detection
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. …
models need to be capable of performing both zero-shot and few-shot intent detection. …
Improving Anti-money Laundering via Fourier-Based Contrastive Learning
M Tong, S Wang, X Chen, J Bei - Pacific-Asia Conference on Knowledge …, 2024 - Springer
… 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 …
contains a total of 10k money laundering transactions and 10M normal transactions. To …
Comparative analysis using supervised learning methods for anti-money laundering in bitcoin
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 …
of Bitcoin blockchain, in which the user's identity is hidden behind a pseudonym known as …
Meta learning for few-shot joint intent detection and slot-filling
HS Bhathiya, U Thayasivam - Proceedings of the 2020 5th International …, 2020 - dl.acm.org
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 …
module in goal oriented conversational agents. Models which optimize these two objectives …
Speeding up deep convolutional neural networks based on tucker-cp decomposition
D Song, P Zhang, F Li - Proceedings of the 2020 5th International …, 2020 - dl.acm.org
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 …
But the computational complexity of CNNs is huge, which makes CNNs run slowly especially …
Domain adaptation based person-specific face anti-spoofing using color texture features
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 …
vulnerable to malicious spoofing attacks such as printed attacks and replayed video attacks. In …
Method for detecting Android malware based on ensemble learning
D Congyi, S Guangshun - Proceedings of the 2020 5th International …, 2020 - dl.acm.org
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 …
operating system mainly used on mobile devices, where hundreds of millions of users can …