Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Pan, Shengfeng"'
Autor:
Murtadha, Ahmed, Pan, Shengfeng, Bo, Wen, Su, Jianlin, Cao, Xinxin, Zhang, Wenze, Liu, Yunfeng
Semi-supervised text classification-based paradigms (SSTC) typically employ the spirit of self-training. The key idea is to train a deep classifier on limited labeled texts and then iteratively predict the unlabeled texts as their pseudo-labels for f
Externí odkaz:
http://arxiv.org/abs/2306.07621
Autor:
Su, Jianlin, Murtadha, Ahmed, Pan, Shengfeng, Hou, Jing, Sun, Jun, Huang, Wanwei, Wen, Bo, Liu, Yunfeng
Named entity recognition (NER) task aims at identifying entities from a piece of text that belong to predefined semantic types such as person, location, organization, etc. The state-of-the-art solutions for flat entities NER commonly suffer from capt
Externí odkaz:
http://arxiv.org/abs/2208.03054
In the era of deep learning, loss functions determine the range of tasks available to models and algorithms. To support the application of deep learning in multi-label classification (MLC) tasks, we propose the ZLPR (zero-bounded log-sum-exp \& pairw
Externí odkaz:
http://arxiv.org/abs/2208.02955
Aspect-based sentiment analysis (ABSA) aims to associate a text with a set of aspects and infer their respective sentimental polarities. State-of-the-art approaches are built on fine-tuning pre-trained language models, focusing on learning aspect-spe
Externí odkaz:
http://arxiv.org/abs/2203.11702
Autor:
Sun, Shaoshi, Zhang, Zhenyuan, Huang, BoCheng, Lei, Pengbin, Su, Jianlin, Pan, Shengfeng, Cao, Jiarun
The softmax function is widely used in artificial neural networks for the multiclass classification problems, where the softmax transformation enforces the output to be positive and sum to one, and the corresponding loss function allows to use maximu
Externí odkaz:
http://arxiv.org/abs/2112.12433
Publikováno v:
In Expert Systems With Applications 15 December 2024 258
Copy mechanisms explicitly obtain unchanged tokens from the source (input) sequence to generate the target (output) sequence under the neural seq2seq framework. However, most of the existing copy mechanisms only consider single word copying from the
Externí odkaz:
http://arxiv.org/abs/2109.12533
Publikováno v:
ICASSP,2021 pp. 3020-3024
Emotion recognition from speech is a challenging task. Re-cent advances in deep learning have led bi-directional recur-rent neural network (Bi-RNN) and attention mechanism as astandard method for speech emotion recognition, extractingand attending mu
Externí odkaz:
http://arxiv.org/abs/2106.04133
Publikováno v:
In Information Sciences March 2024 661
Publikováno v:
In Neurocomputing 1 February 2024 568