---
title: nlp_structbert_siamese-aoe_chinese-base
canonical_url: "https://www.modelscope.cn/models/iic/nlp_structbert_siamese-aoe_chinese-base"
md_url: "https://www.modelscope.cn/models/iic/nlp_structbert_siamese-aoe_chinese-base.md"
repository: iic/nlp_structbert_siamese-aoe_chinese-base
chinese_name: "SiameseAOE通用属性观点抽取-中文-base"
last_updated: 2025-12-16
license: "Apache License 2.0"
pipeline_tag: siamese-uie
tasks:
  - siamese-uie
  - relation-extraction
  - token-classification
  - sentiment-classification
  - universal-information-extraction
model_type:
  - bert
library_name:
  - pytorch
frameworks:
  - pytorch
language:
  - cn
domain:
  - nlp
downloads: 61989
stars: 24
tags:
  - "情感分析"
  - "属性情感抽取"
  - transformer
  - AliceMind
  - Alibaba
---

# nlp_structbert_siamese-aoe_chinese-base

> nlp_structbert_siamese-aoe_chinese-base - iic 在 ModelScope 开源的模型。SiameseAOE通用属性情感抽取介绍

iic/nlp_structbert_siamese-aoe_chinese-base 是 ModelScope 魔搭社区上的siamese-uie、relation-extraction、token-classification模型，采用 Apache License 2.0 许可。

- **Repository**: iic/nlp_structbert_siamese-aoe_chinese-base
- **License**: Apache License 2.0
- **Tasks**: siamese-uie, relation-extraction, token-classification, sentiment-classification, universal-information-extraction
- **Tags**: 情感分析, 属性情感抽取, transformer, AliceMind, Alibaba
- **Downloads**: 61989
- **Stars**: 24
- **Last updated**: 2025-12-16

Source: https://www.modelscope.cn/models/iic/nlp_structbert_siamese-aoe_chinese-base

---

# SiameseAOE通用属性情感抽取介绍

SiameseAOE通用信息抽取模型，基于提示（Prompt）+文本（Text）的构建思路，利用指针网络（Pointer Network）实现片段抽取（Span Extraction），从而实现各类属性情感抽取（ABSA）任务的抽取。该模型基于[SiameseUIE](https://modelscope.cn/models/damo/nlp_structbert_siamese-uie_chinese-base/summary)框架，在500w条ABSA标注数据集进行预训练。

## 模型描述

模型基于structbert-base-chinese在500w条ABSA标注数据集训练得到，模型框架如下图：

![](model.jpg)

## 期望模型使用方式以及适用范围
你可以使用该模型，实现各类属性情感抽取（ABSA）任务。

### 如何使用

#### 安装Modelscope

依据ModelScope的介绍，实验环境可分为两种情况。在此推荐使用第2种方式，点开就能用，省去本地安装环境的麻烦，直接体验ModelScope。

##### 1 本地环境安装

可参考[ModelScope环境安装](https://www.modelscope.cn/?spm=a2c6h.12873639.article-detail.7.59b93bc77Qw9sE#/docs/环境安装)。

##### 2 Notebook

ModelScope直接集成了线上开发环境，用户可以直接在线训练、调用模型。

打开模型页面，点击右上角“在Notebook中打开”，选择机器型号后，即可进入线上开发环境。

#### 代码范例
##### Fine-Tune 微调示例
```python
import os
import json
from modelscope.trainers import build_trainer
from modelscope.msdatasets import MsDataset
from modelscope.utils.hub import read_config
from modelscope.metainfo import Metrics
from modelscope.utils.constant import DownloadMode


model_id = 'damo/nlp_structbert_siamese-aoe_chinese-base'

WORK_DIR = '/tmp'

train_dataset = MsDataset.load('absa_aoe', namespace='damo', split='train', download_mode=DownloadMode.FORCE_REDOWNLOAD)
eval_dataset = MsDataset.load('absa_aoe', namespace='damo', split='validation', download_mode=DownloadMode.FORCE_REDOWNLOAD)


max_epochs=3
kwargs = dict(
    model=model_id,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    max_epochs=max_epochs,
    work_dir=WORK_DIR)


trainer = build_trainer('siamese-uie-trainer', default_args=kwargs)

print('===============================================================')
print('pre-trained model loaded, training started:')
print('===============================================================')

trainer.train()

print('===============================================================')
print('train success.')
print('===============================================================')

for i in range(max_epochs):
    eval_results = trainer.evaluate(f'{WORK_DIR}/epoch_{i+1}.pth')
    print(f'epoch {i} evaluation result:')
    print(eval_results)


print('===============================================================')
print('evaluate success')
print('===============================================================')
```

##### 零样本推理示例
```python
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

semantic_cls = pipeline(Tasks.siamese_uie, 'damo/nlp_structbert_siamese-aoe_chinese-base', model_revision='master')

# AOE模型仅支持以下这几种Schema
# 属性情感抽取 {属性词: {情感词: None}}
semantic_cls(
	input='很满意，音质很好，发货速度快，值得购买', 
  	schema={
        '属性词': {
            '情感词': None,
        }
    }
) 
# 允许属性词缺省，#表示缺省
semantic_cls(
	input='#很满意，音质很好，发货速度快，值得购买', 
  	schema={
        '属性词': {
            '情感词': None,
        }
    }
) 
# 支持情感分类
semantic_cls(
	input='很满意，音质很好，发货速度快，值得购买', 
  	schema={
        '属性词': {
            "正向情感(情感词)": None, 
            "负向情感(情感词)": None, 
            "中性情感(情感词)": None
        }
    }
) 
```
### 模型局限性以及可能的偏差
模型训练数据有限，在特定行业数据上，效果可能存在一定偏差。

## 数据评估及结果


### 相关论文以及引用信息

```bib
@article{wang2019structbert,
  title={Structbert: Incorporating language structures into pre-training for deep language understanding},
  author={Wang, Wei and Bi, Bin and Yan, Ming and Wu, Chen and Bao, Zuyi and Xia, Jiangnan and Peng, Liwei and Si, Luo},
  journal={arXiv preprint arXiv:1908.04577},
  year={2019}
}
@inproceedings{Zhao2021AdjacencyLO,
  title={Adjacency List Oriented Relational Fact Extraction via Adaptive Multi-task Learning},
  author={Fubang Zhao and Zhuoren Jiang and Yangyang Kang and Changlong Sun and Xiaozhong Liu},
  booktitle={FINDINGS},
  year={2021}
}
```