All systems operationalAI Agent Automation Platform
English
Language简体中文EnglishSelected

Choose your language

Erlangshen-Roberta-330M-Causal-Chinese

Fengshenbang/Erlangshen-Roberta-330M-Causal-Chinese

PublisherFengshenbang

Download access requirementsModelScope source

Erlangshen-Roberta-330M-Causal-Chinese Github: Fengshenbang-LM Docs: Fengshenbang-Docs

Text Processing
Model details

模型介绍

中文整理

Erlangshen-Roberta-330M-Causal-Chinese

Github: Fengshenbang-LM

Docs: Fengshenbang-Docs

简介 Brief Introduction

基于chinese-roberta-wwm-ext-large模型继续训练得到的中文因果关系判别模型。

This is a Chinese causality discriminative model trained from chinese-roberta-wwm-ext-large.

模型分类 Model Taxonomy

需求 Demand 任务 Task 系列 Series 模型 Model 参数 Parameter 额外 Extra

:----: :----: :----: :----: :----: :----:

通用 General 自然语言理解 NLU 二郎神 Erlangshen Roberta 330M 中文-因果关系推断 Chinese-Causal

模型信息 Model Information

数据准备 Corpus Preparation

因果语料库:同Randeng-TransformerXL-5B-Deduction-Chinese,基于悟道语料库(280G版本),通过关联词匹配、人工标注 + GTSFactory筛选、数据清洗等步骤获取的具有因果关系的句子对

重构NLI数据:对CMNLI、OCNLI数据集进行数据清洗,并将“蕴含”类别作为正例、其余类别作为负例转换为二分类数据集

预热数据集:以重构后的CMNLI数据集为基础,引入因果语料库样本平衡正负例数量

Wudao Causal Corpus: Based on the Wudao corpus (280G version), sentence pairs with causality were obtained through logic indicator matching, manual annotation + GTSFactory, and data cleaning.

Reconstructed NLI data: After cleaning cmnli and ocnli dataset, we converted them into binary datasets by taking the "Entail" category as positive category and others as the negative.

Warm-up dataset: Based on the reconstructed cmnli dataset, the number of each category is balanced using data from the Wudao Causal Corpus.

模型训练 Model Training

  • 基于chinese-roberta-wwm-ext-large模型,在预热数据集上微调预热
  • 作为判别模型与Randeng-TransformerXL-5B-Deduction-Chinese模型和Randeng-TransformerXL-5B-Abduction-Chinese模型进行自洽(Self-consistent)闭环训练:
  • 将预热数据集中样本的句子对拆散,分别作为原因和结果输入至Randeng-TransformerXL-5B-Deduction-Chinese模型和Randeng-TransformerXL-5B-Abduction-Chinese模型。两个生成模型基于核采样和贪心的方式进行因果推理和反绎推理,产生大量伪样本;
  • 本模型对伪样本句子对的因果关系进行打分,筛选供自身以及生成模型训练的样本

First, we fine-tuned chinese-roberta-wwm-ext-large model on our warm-up dataset.

Then, we conducted self-consistent learning on this model, cooperating with Randeng-TransformerXL-5B-Deduction-Chinese model and Randeng-TransformerXL-5B-Abduction-Chinese model.

Specifically, sentence pairs in the warm-up dataset were split and feed into Randeng-TransformerXL-5B-Deduction-Chinese model and Randeng-TransformerXL-5B-Abduction-Chinese model as premise and result respectively.

Two generative models performed deductive reasoning and abductive reasoning based on each sample respectively, generating a large number of pseudo-samples; Erlangshen-Roberta-330M-Causal-Chinese scored the causality of the pseudo-samples and selected the training data for itself and the generative models in the next iteration.

模型效果 Performance for reference

Warmup dataset (dev) Warmup dataset (test) ocnli (Zero-shot)

:--------: :-----: :----: :----:

F1-score 84.06 84.04 78.43

Precision 79.95 79.71 81.51

Recall 88.63 88.88 75.57

使用 Usage

引用 Citation

如果您在您的工作中使用了我们的模型,可以引用我们的论文:

If you are using the resource for your work, please cite the our paper:

也可以引用我们的网站:

You can also cite our website:

优先采用原作者提供的中文模型卡片;仅有英文说明时由闲社AI翻译整理。重要参数、许可证和商用范围请以原文为准。

你将获得什么

完整仓库方式包含该固定版本中的权重、配置、分词器及说明文件;指定版本方式只下载所选文件或整组分片。多模态模型的投影文件、配置等依赖,请按作者说明配齐。

完整仓库可能包含多个权重格式,因此需要的磁盘空间可能大于单一格式的模型大小。下载文件不等于完成模型部署。

使用前须知

运行环境

运行模型需要的设备、工具与依赖,以原作者说明为准。

授权范围

是否允许商用、修改和分发,请查看模型许可证。

闲社提供资料与镜像下载方法,不代表已运行模型或完成安全审计。下载的代码应先检查,再执行。

Back to top