SeqXGPT: Sentence-level AI-generated text detection
Widely applied large language models (LLMs) can generate human-like content, raising
concerns about the abuse of LLMs. Therefore, it is important to build strong AI-generated text …
concerns about the abuse of LLMs. Therefore, it is important to build strong AI-generated text …
A novel masking model for Buddhist literature understanding by using Generative Adversarial Networks
C Yan, Y Wang, L Chang, Q Zhang, T He - Expert Systems with Applications, 2024 - Elsevier
This paper is focused on ancient Chinese Buddhist literature understanding. Buddhist
literature incorporates a plethora of dialects and slang, which makes it challenging to extract …
literature incorporates a plethora of dialects and slang, which makes it challenging to extract …
Semantic-enhanced graph neural network for named entity recognition in ancient Chinese books
Y Xu, C Mao, Z Wang, G Jin, liangji Zhong, T Qian - Scientific Reports, 2024 - nature.com
Named entity recognition (NER) plays a crucial role in the extraction and utilization of
knowledge of ancient Chinese books. However, the challenges of ancient Chinese NER not …
knowledge of ancient Chinese books. However, the challenges of ancient Chinese NER not …
AC-EVAL: Evaluating Ancient Chinese Language Understanding in Large Language Models
Given the importance of ancient Chinese in capturing the essence of rich historical and
cultural heritage, the rapid advancements in Large Language Models (LLMs) necessitate …
cultural heritage, the rapid advancements in Large Language Models (LLMs) necessitate …
A Multi-task Framework with Enhanced Hierarchical Attention for Sentiment Analysis on Classical Chinese Poetry: Utilizing Information from Short Lines
Classical Chinese poetry has a long history, dating back to the 11th century BC. By
investigating the sentiment expressed in the poetry, we can gain more insights in the …
investigating the sentiment expressed in the poetry, we can gain more insights in the …
Named Entity Recognition in Classical Chinese by Lexicon Enhancement
J Yu, X Feng, J Li, J Liu - 2023 IEEE International Conference …, 2023 - ieeexplore.ieee.org
The significant differences between classical Chinese and modern Chinese make the NER
methods that are applicable to modern Chinese not applicable to classical Chinese. In this …
methods that are applicable to modern Chinese not applicable to classical Chinese. In this …
融合词典信息的古籍命名实体识别研究(A Study on the Recognition of Named Entities of Ancient Books Using Lexical Information)
W Kang, J Zuo, A Jie, W Luo… - Proceedings of the 22nd …, 2023 - aclanthology.org
Abstract “古籍命名实体识别对于古籍实体知识库与语料库的建设具有显著的现实意义.
目前古籍命名实体识别的研究较少, 主要原因是缺乏足够的训练语料. 本文从《 资治通鉴》 入手 …
目前古籍命名实体识别的研究较少, 主要原因是缺乏足够的训练语料. 本文从《 资治通鉴》 入手 …
Unlocking transitional Chinese: word segmentation in modern historical texts
Abstract This research addresses Natural Language Processing (NLP) tokenization
challenges for transitional Chinese, which lacks adequate digital resources. The project …
challenges for transitional Chinese, which lacks adequate digital resources. The project …
古农文语义检索模型构建及其应用研究
刘楠竹， 崔运鹏， 王末 - 农业图书情报学报, 2023 - nytsqb.aiijournal.com
摘要院[目的/意义] 构建能实现以白话文作为查询, 系统自动返回与输入最相关的古农文段落的
语义检索模型, 为学者提供更加便利的古代农业知识检索方式和古代农业知识溯源方式.[方法 …
语义检索模型, 为学者提供更加便利的古代农业知识检索方式和古代农业知识溯源方式.[方法 …
Research on Named Entity Recognition in Ancient Chinese Based on Incremental Pre-training and Domain Lexicon
W Kang, J Zuo, Q Dai, Y Hu, M Wang - CCF International Conference on …, 2024 - Springer
Currently, there is limited research on ancient Chinese named entity recognition, primarily
due to the scarcity of publicly available datasets for model training. We constructed a CMAG …
due to the scarcity of publicly available datasets for model training. We constructed a CMAG …