guogene / nlp_ann
nlp标注平台 前端/后端
☆16Updated 3 years ago
Alternatives and similar repositories for nlp_ann:
Users that are interested in nlp_ann are comparing it to the libraries listed below
- 通用版面分析 | 中 文文档解析 |Document Layout Analysis | layout paser☆46Updated 9 months ago
- chinese document classification of layoutlmv3 and layoutxlm☆43Updated 2 years ago
- 文档图片表格结构识别算法-同花顺算法挑战赛-2022年2-4月春季赛☆25Updated 3 years ago
- 基于Qwen2模型进行通用信息抽取【实体/关系/事件抽取】☆30Updated 8 months ago
- TensorRT☆11Updated 4 years ago
- Bert TensorRT模型加速部署☆9Updated 2 years ago
- 一个非常高效的字符串匹配工具,支持正向/反向最大匹配分词和多模式字符串精确匹配☆17Updated last year
- Graph QABot Demo| 图谱问答案例☆15Updated last year
- 中文版面检测(Chinese layout detection),yolov8 is used to detect the layout of Chinese document images。☆59Updated last year
- BLOOM 模型的指令微调☆24Updated last year
- 可以成功Lora微调的Qwen-VL模型☆18Updated last year
- Let ChatGPT (Large Language Models) Serve As Data Annotator and Zero-shot/few-shot Information Extractor.☆31Updated 2 years ago
- 该项目是为了使用layoutlmv3针对中文图片训练和推理。 其中主要解决三个问题: 1.数据标准化成可以的训练数据集格式 2.layoutlmv3-base-chinese 分词修改 2.超过512长度的文本切分和滑窗操作☆44Updated 6 months ago
- PaddleOCR 输出结果的行对齐,表格制式图像OCR行对齐☆44Updated 3 years ago
- multi-task classifier☆22Updated last year
- LLM for NER☆68Updated 7 months ago
- 纯c++的全平台llm加速库,支持python调用,支持baichuan, glm, llama, moss基座,手机端流畅运行chatglm-6B级模型单卡可达10000+token / s,☆45Updated last year
- 基于sentence-transformers实现文本转向量的机器人☆45Updated 2 years ago
- benchmark of KgCLUE, with different models and methods☆27Updated 3 years ago
- ☆26Updated 5 months ago
- Chinese MobileBERT(中文MobileBERT模型)☆89Updated 3 years ago
- deep training task☆29Updated last year
- intent detection and slot filling 意图识别与槽填充联合模型☆37Updated 2 years ago
- t5-model-onnx,中文拼 写纠错,Chinese spelling correction。☆14Updated 2 years ago
- lightweighted deep learning inference service framework☆39Updated 3 years ago
- Sentence-Transformers Information Retrieval example on Chinese☆29Updated last year
- 大模型API性能指标比较 - 深入分析TTFT、TPS等关键指标☆13Updated 6 months ago
- ☆57Updated 2 years ago
- 本项目由三个模块构成。意图识别:判断用户的意图是业务型还是闲聊型;模型检索:该部分构建一个语料库,当用户 发起新的query(通过意图识别判断为业务型对话) 时,为用户匹配query检索的最佳response,使用HSWN进行召回(粗排), 然后构建句子的相似度,并利用Lig…☆10Updated 4 years ago
- [Paper] Code for the EMNLP2023 (Findings) paper "Global Structure Knowledge-Guided Relation Extraction Method for Visually-Rich Document"☆17Updated last year