BiLGAT: Bidirectional lattice graph attention network for chinese short text classification
P Lyu, G Rao, L Zhang, Q Cong - Applied Intelligence, 2023 - Springer
Chinese short text classification approaches based on lexicon information and pretrained
language models have yielded state-of-the-art results. However, they simply use the …
language models have yielded state-of-the-art results. However, they simply use the …
A survey of multi-label text classification based on deep learning
X Chen, J Cheng, J Liu, W Xu, S Hua, Z Tang… - … Conference on Adaptive …, 2022 - Springer
Text classification (TC) is an important basic task in the field of Natural Language
Processing (NLP), and multi-label text classification (MLTC) is an important branch of TC …
Processing (NLP), and multi-label text classification (MLTC) is an important branch of TC …
Multi-granularity interaction model based on pinyins and radicals for Chinese semantic matching
Semantic matching plays a critical role in many downstream tasks of natural language
processing. Existing semantic matching methods, which focus on learning sentence …
processing. Existing semantic matching methods, which focus on learning sentence …
ZiNet: Linking Chinese characters spanning three thousand years
Modern Chinese characters evolved from 3,000 years ago. Up to now, tens of thousands of
glyphs of ancient characters have been discovered, which must be deciphered by experts to …
glyphs of ancient characters have been discovered, which must be deciphered by experts to …
RS-BERT: Pre-training radical enhanced sense embedding for Chinese word sense disambiguation
Word sense disambiguation is a crucial task to test whether a model can perform deep
understanding. Nowadays, the rise of pre-trained language models facilitates substantial …
understanding. Nowadays, the rise of pre-trained language models facilitates substantial …
Text Classification via Learning Semantic Dependency and Association
Text classification is a fundamental and classical problem in natural language processing.
Existing methods in this area attach more attention to structure modeling of texts, while …
Existing methods in this area attach more attention to structure modeling of texts, while …
A Chinese text classification model based on radicals and character distinctions
H Yan-Xin, L Bo - IEEE Access, 2023 - ieeexplore.ieee.org
Chinese characters are generally correlated with their semantic meanings, and the structure
of radicals, in particular, can be a clear indication of how characters are related to each …
of radicals, in particular, can be a clear indication of how characters are related to each …
A Sentence-Matching Model Based on Multi-Granularity Contextual Key Semantic Interaction
J Li, Y Li - Applied Sciences, 2024 - mdpi.com
In the task of matching Chinese sentences, the key semantics within sentences and the
deep interaction between them significantly affect the matching performance. However …
deep interaction between them significantly affect the matching performance. However …
Learning from ideography and labels: A schema-aware radical-guided associative model for chinese text classification
Reading psychology believes text comprehension to involve a complex psychological
construction process, with the reader mind being a dynamic associative system that stores …
construction process, with the reader mind being a dynamic associative system that stores …
Same-radical Character Association Model in Text Classification
Y Gao, X Peng - IEEE Transactions on Consumer Electronics, 2023 - ieeexplore.ieee.org
Research has verified that associative learning will improve learning efficiency during the
process of recognizing Chinese characters. Therefore, some scholars believe that the …
process of recognizing Chinese characters. Therefore, some scholars believe that the …