Using Chinese Glyphs for Named Entity Recognition (Student Abstract)

Song, Chan; Sehanobish, Arijit

doi:10.1609/aaai.v34i10.7233

Cited by 13 publications

(8 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This indicates that Simplified Lattice does not exploit the full potential of BERT-wwm-ext. GLYNN [21] improved the performance of Chinese NER by using a CNN encoder to integrate glyph features from character images, indicating that Chinese NER can benefit from the pictogram features. The SLRL-NER model integrates lexicon, character, and radical-level features leads to 0.47 and 0.25 increments of F1 score over the state of-the-art model on OntoNotes 4.0 and Resume, respectively.…”

Section: B Experimental Resultsmentioning

confidence: 99%

Exp-SoftLexicon Lattice Model Integrating Radical-Level Features for Chinese NER

Li¹,

Hu²,

Chen³

et al. 2022

International Conferences on Software Engineering and Knowledge Engineering

View full text Add to dashboard Cite

The Lattice series model using potential words information has been proved to be effective in Chinese Named Entity Recognition (NER). The recently proposed Simplified Lattice not only brings new baseline results, but also improves the inference speed of Lattice models. However, the Simplified Lattice fails to fully explore the rich information contained in the radical-level features of the character sequences. Moreover, the performance of the Simplified Lattice decreases dramatically as the length of entity increases. In this paper, we propose the SLRL-NER model that integrates word, character, and radical-level information to alleviate the above problems. Specifically, text Convolutional Neural Network (CNN) is used to extract the radical-level features. The original SoftLexicon set is expanded to refine the relative position information of characters in the candidate words to cope with the challenge of increasing entity length. Experiments on three datasets show SLRL-NER outperforms the state-of-the-art comparison methods.

show abstract

Section: B Experimental Resultsmentioning

confidence: 99%

Exp-SoftLexicon Lattice Model Integrating Radical-Level Features for Chinese NER

Li¹,

Hu²,

Chen³

et al. 2022

International Conferences on Software Engineering and Knowledge Engineering

View full text Add to dashboard Cite

show abstract

“…The interactive knowledge between the glyph and context is ignored. Second, the entity type and quantity of modern Chinese are far richer and more complex than those of ancient Chinese, it has been proven that historical texts are meaningless to NER, to some extent [ 25 ].…”

Section: Related Workmentioning

confidence: 99%

Kcr-FLAT: A Chinese-Named Entity Recognition Model with Enhanced Semantic Information

Deng

Tao

Lan

et al. 2023

Sensors

View full text Add to dashboard Cite

The performance of Chinese-named entity recognition (NER) has improved via word enhancement or new frameworks that incorporate various types of external data. However, for Chinese NER, syntactic composition (in sentence level) and inner regularity (in character-level) have rarely been studied. Chinese characters are highly sensitive to sentential syntactic data. The same Chinese character sequence can be decomposed into different combinations of words according to how they are used and placed in the context. In addition, the same type of entities usually have the same naming rules due to the specificity of the Chinese language structure. This paper presents a Kcr-FLAT to improve the performance of Chinese NER with enhanced semantic information. Specifically, we first extract different types of syntactic data, functionalize the syntactic information by a key-value memory network (KVMN), and fuse them by attention mechanism. Then the syntactic information and lexical information are integrated by a cross-transformer. Finally, we use an inner regularity perception module to capture the internal regularity of each entity for better entity type prediction. The experimental results show that with F1 scores as the evaluation index, the proposed model obtains 96.51%, 96.81%, and 70.12% accuracy rates on MSRA, resume, and Weibo datasets, respectively.

show abstract

“…Meng et al [36] proposed a Tianzige-CNN to capture the graphic features of the Traditional Chinese that contain more pictographic information. Song and Sehanobish [29] also proposed Table 9: An example from OntoNotes4.0 dataset. Characters colored in blue and red represent the correct and incorrect recognized entity, respectively.…”

Section: Related Workmentioning

confidence: 99%

Pretraining Multi-modal Representations for Chinese NER Task with Cross-Modality Attention

Mai

Qiu

Luo

et al. 2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Named Entity Recognition (NER) aims to identify the pre-defined entities from the unstructured text. Compared with English NER, Chinese NER faces more challenges: the ambiguity problem in entity boundary recognition due to unavailable explicit delimiters between Chinese characters, and the out-of-vocabulary (OOV) problem caused by rare Chinese characters. However, two important features specific to the Chinese language are ignored by previous studies: glyphs and phonetics, which contain rich semantic information of Chinese. To overcome these issues by exploiting the linguistic potential of Chinese as a logographic language, we present MPM-CNER (short for Multi-modal Pretraining Model for Chinese NER), a model for learning multi-modal representations of Chinese semantics, glyphs, and phonetics, via four pretraining tasks: Radical Consistency Identification (RCI), Glyph Image Classification (GIC), Phonetic Consistency Identification (PCI), and Phonetic Classification Modeling (PCM). Meanwhile, a novel cross-modality attention mechanism is proposed to fuse these multimodal features for further improvement. The experimental results show that our method outperforms the state-of-the-art baseline methods on four benchmark datasets, and the ablation study also verifies the effectiveness of the pre-trained multi-modal representations.

show abstract

Using Chinese Glyphs for Named Entity Recognition (Student Abstract)

Cited by 13 publications

References 2 publications

Exp-SoftLexicon Lattice Model Integrating Radical-Level Features for Chinese NER

Exp-SoftLexicon Lattice Model Integrating Radical-Level Features for Chinese NER

Kcr-FLAT: A Chinese-Named Entity Recognition Model with Enhanced Semantic Information

Pretraining Multi-modal Representations for Chinese NER Task with Cross-Modality Attention

Contact Info

Product

Resources

About