语言:

• 葡萄牙语 标签:
• 命名实体识别 指标:
• F1值
• 准确率
• 精确率
• 召回率

RiskData 巴西葡萄牙语命名实体识别模型

模型描述

本模型是基于Neuralmind BERTimbau针对葡萄牙语进行微调的版本。

使用场景与限制

使用方法

from transformers import BertForTokenClassification, DistilBertTokenizerFast, pipeline
model = BertForTokenClassification.from_pretrained('monilouise/ner_pt_br')
tokenizer = DistilBertTokenizerFast.from_pretrained('neuralmind/bert-base-portuguese-cased'
                                                    , model_max_length=512
                                                    , do_lower_case=False
                                                    )
nlp = pipeline('ner', model=model, tokenizer=tokenizer, grouped_entities=True)
result = nlp("联邦审计法院位于巴西利亚，由鲁伊·巴尔博萨创立。")

局限性及偏差

• 该微调模型的训练语料包含约180篇从谷歌新闻抓取的新闻文章。原项目旨在识别与欺诈和腐败相关新闻中的命名实体，并将这些实体分为四类：人物（PERSON）、组织（ORGANIZATION）、公共机构（PUBLIC INSTITUTION）和地点（LOCAL）。

训练流程

评估结果

准确率: 0.98, 精确率: 0.86 召回率: 0.91 F1值: 0.88

评分通过以下代码计算：

    def align_predictions(predictions: np.ndarray, label_ids: np.ndarray) -> Tuple[List[int], List[int]]:
        preds = np.argmax(predictions, axis=2)
        batch_size, seq_len = preds.shape
        out_label_list = [[] for _ in range(batch_size)]
        preds_list = [[] for _ in range(batch_size)]

        for i in range(batch_size):
            for j in range(seq_len):
                if label_ids[i, j] != nn.CrossEntropyLoss().ignore_index:
                    out_label_list[i].append(id2tag[label_ids[i][j]])
                    preds_list[i].append(id2tag[preds[i][j]])

        return preds_list, out_label_list

    def compute_metrics(p: EvalPrediction) -> Dict:
        preds_list, out_label_list = align_predictions(p.predictions, p.label_ids)
        return {
            "accuracy_score": accuracy_score(out_label_list, preds_list),
            "precision": precision_score(out_label_list, preds_list),
            "recall": recall_score(out_label_list, preds_list),
            "f1": f1_score(out_label_list, preds_list),
        }

参考文献及引用信息

有关BERTimbau语言模型的更多信息：

@inproceedings{souza2020bertimbau,
    author    = {Souza, F{\'a}bio and Nogueira, Rodrigo and Lotufo, Roberto},
    title     = {{BERT}imbau: pretrained {BERT} models for {B}razilian {P}ortuguese},
    booktitle = {9th Brazilian Conference on Intelligent Systems, {BRACIS}, Rio Grande do Sul, Brazil, October 20-23 (to appear)},
    year      = {2020}
}

@article{souza2019portuguese,
    title={Portuguese Named Entity Recognition using BERT-CRF},
    author={Souza, F{\'a}bio and Nogueira, Rodrigo and Lotufo, Roberto},
    journal={arXiv preprint arXiv:1909.10649},
    url={http://arxiv.org/abs/1909.10649},
    year={2019}
}