JobBERT-zh initialization

Domain-adapted Chinese recruitment encoder with an inherited CRF checkpoint.

Project · Data · Reproduction guide

Use this model

Span extraction requires the Transformers encoder together with the custom BertCRF class and CRF checkpoint. See loading and technical details for the custom model class and checkpoint paths.

The model predicts flat character spans in Chinese job advertisements using language (L), knowledge (K), occupational-skill (S), and transversal-competence (T) labels. Its task is to identify competency wording in source text.

Checkpoint role

This repository supplies the domain-adapted encoder and CRF used to initialize the later supervision study. The historical exact F1 of 0.4331 uses a hybrid 2,601-record reference and jieba span alignment. The Silver fine-tuned model is evaluated on the human reference set using typed character-span scoring.

File	Purpose
model.safetensors and configuration/tokenizer files	Domain-adapted encoder
crf/best.pt	Inherited CRF checkpoint

Access and scope

The model licence remains other; source-text permissions differ from the software licence. Use for research on recruitment text, with appropriate data permissions and validation. Applicant profiling and automated hiring decisions are outside the intended use.

Recruitment texts in Chinese-SkillSpan were obtained through three routes: purchased collections from MacroData (马克数据网), operated by 重庆马禾锐信息科技有限公司; research-team collection of public recruitment pages across regions of China; and the 招聘数据集 / Recruitment Dataset, ID 163746 on Alibaba Cloud Tianchi. For the public-institution subset, team members manually identified pages, registered selected URLs in a crawling framework that revisited those sources on weekly or monthly schedules, and then screened and cleaned the records. The source composition of the 3M pretraining corpus remains undocumented. See data sources and collection. Source-text reuse remains subject to the original providers' terms and the project's documented access conditions.

Loading instructions, checkpoint information, and evaluation details are in TECHNICAL_DETAILS.md. The model-name index maps manuscript names to exact model IDs. The resource naming guide also maps descriptive data names to preserved archive identifiers.