paper-with-me

Papers

HREB-CRF: Hierarchical Reduced-bias EMA for Chinese Named Entity Recognition

2025-03-03 · Sijin Sun, Ming Deng, Xinrui Yu, Liangbin Zhao

Incorrect boundary division, complex semantic representation, and differences in pronunciation and meaning often lead to errors in Chinese Named Entity Recognition(CNER). To address these issues, this paper proposes HREB-CRF framework: Hierarchical Reduced-bias EMA with CRF. The proposed method amplifies word boundaries and pools long text gradients through exponentially fixed-bias weighted average of local and global hierarchical attention. Experimental results on the MSRA, Resume, and Weibo datasets show excellent in F1, outperforming the baseline model by 1.1\%, 1.6\%, and 9.8\%. The significant improvement in F1 shows evidences of strong effectiveness and robustness of approach in CNER tasks.

📄 PDF Abstract BibTeX arXiv:2503.01217

Code (1)

StanleySun233/HREB-CRF 공식 구현 pytorch

Tasks

Chinese Named Entity Recognitionnamed-entity-recognitionNamed Entity Recognition

Methods 이 논문이 사용한 방법론

CRF Conditional Random Fields or CRFs are a type of probabilistic graph model that take neighboring sample context into account for tasks like classification. Prediction is…

Similar Papers 제목 키워드 기반

Chinese Named Entity Recognition via Adaptive Multi-pass Memory Network with Hierarchical Tagging Mechanism

2020-10-01 · CCL 2020 10 · Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

Named entity recognition (NER) aims to identify text spans that mention named entities and classify them into pre-defined categories. For Chinese NER task, most of the existing methods are character-based sequence labeli…

Chinese Named Entity Recognitionnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+2

Multiple-Debias: A Full-process Debiasing Method for Multilingual Pre-trained Language Models

2026-04-03 · Haoyu Liang, Peijian Zeng, Wentao Huang, Aimin Yang 외 arxiv

Multilingual Pre-trained Language Models (MPLMs) have become essential tools for natural language processing. However, they often exhibit biases related to sensitive attributes such as gender, race, and religion. In this…

parameter-efficient fine-tuningData Augmentation

Promoting the linguistic diversity of TEI in the Maghreb and the Arab region

2024-04-16 · Henri Hudrisier, Rachid Zghibi, Sihem Zghidi, Mokhtar Ben Henda

The project targets both oral corpus and the rich text resources written in the Maghreb region. It focuses particularly on the continuity, for more than 12 centuries, of a classical still alive Arabic language and on the…

Diversity

BigCilin: An Automatic Chinese Open-domain Knowledge Graph with Fine-grained Hypernym-Hyponym Relations

2022-11-07 · Ming Liu, Yaojia LV, Jingrun Zhang, Ruiji Fu 외

This paper presents BigCilin, the first Chinese open-domain knowledge graph with fine-grained hypernym-hyponym re-lations which are extracted automatically from multiple sources for Chinese named entities. With the fine-…

Hrebs and Cohesion Chains as similar tools for semantic text properties research

2014-01-15 · D. Tatar, M. Lupea, E. Kapetanios

In this study it is proven that the Hrebs used in Denotation analysis of texts and Cohesion Chains (defined as a fusion between Lexical Chains and Coreference Chains) represent similar linguistic tools. This result gives…