The pre-training of text encoders normally processes text as a sequence of tokens corresponding to small text units, such as word pieces in English and characters in Chinese …
Y Nie, Y Tian, Y Song, X Ao, X Wan - arXiv preprint arXiv:2010.15466, 2020 - arxiv.org
Named entity recognition (NER) is highly sensitive to sentential syntactic and semantic properties where entities may be extracted according to how they are used and placed in the …
Y Tian, Y Song, F Xia, T Zhang… - Proceedings of the 58th …, 2020 - aclanthology.org
Contextual features always play an important role in Chinese word segmentation (CWS). Wordhood information, being one of the contextual features, is proved to be useful in many …
Large pre-trained models such as BERT are known to improve different downstream NLP tasks, even when such a model is trained on a generic domain. Moreover, recent studies …
Y Song, Y Tian, N Wang, F Xia - Proceedings of the 28th …, 2020 - aclanthology.org
Summarization is an important natural language processing (NLP) task in identifying key information from text. For conversations, the summarization systems need to extract salient …
Y Tian, Y Song, F Xia - … of the 28th International Conference on …, 2020 - aclanthology.org
Chinese word segmentation (CWS) and part-of-speech (POS) tagging are two fundamental tasks for Chinese language processing. Previous studies have demonstrated that jointly …
In the last decade, blockchain smart contracts emerged as an automated, decentralized, traceable, and immutable medium of value exchange. Nevertheless, existing blockchain …
P Jiang, D Long, Y Zhang, P Xie, M Zhang… - arXiv preprint arXiv …, 2022 - arxiv.org
Boundary information is critical for various Chinese language processing tasks, such as word segmentation, part-of-speech tagging, and named entity recognition. Previous studies …
Q He, G Chen, W Song, P Zhang - Applied Sciences, 2023 - mdpi.com
Named entity recognition (NER) is a subfield of natural language processing (NLP) that identifies and classifies entities from plain text, such as people, organizations, locations, and …