中文口语StructBERT问句识别任务

基于StructBERT的中文Base预训练模型介绍

StructBERT的中文Large预训练模型是使用wikipedia数据和masked language model任务训练的中文自然语言理解预训练模型（预训练基座模型见 https://modelscope.cn/models/damo/nlp_structbert_spoken_chinese-base/summary ）。可以用于下游的nlu自然语言理解任务训练。

问句识别模型描述

StructBERT-spoken-base 预训练模型是使用structbert-base中文自然语言理解预训练模型在大量口语数据上使用MLM+口语化与训练目标继续进行预训练得到的。可以用于下游的nlu自然语言理解任务训练。在预训练模型的基础上我们利用问句识别任务（判断句子是否为为问句）。

期望模型使用方式以及适用范围

本模型主要用于给在输入文档中发现问句。用户可以自行尝试各种输入文档。具体调用方式请参考代码示例。

如何使用

在安装完成ModelScope-library之后即可使用text-generation的能力

预测代码范例

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from modelscope.outputs import OutputKeys

text_classification = pipeline(Tasks.text_classification, model='damo/nlp_structbert_alimeeting_action-classification_chinese-base')
output = text_classification("今天会议的第一个结论是明天先收集用户的需求吗？")

模型局限性以及可能的偏差

模型在相关访谈数据集上训练，在会议等类似内容上性能较好，其他垂直领域效果可能会有所下降。

模型训练流程

用户可以基于这个StructBERT预训练底座模型进一步优化，训练代码如下，更详细代码请参考 alimeeting4mug

from datasets import Dataset
import os.path as osp
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 Tasks



# ---------------------------- Train ---------------------------------

model_id = 'damo/nlp_structbert_backbone_base_std'
WORK_DIR = 'workspace'
data_pth = "meeting_action"
def load_local_data(data_pth):
    train_dataset_dict = {"label": [], "sentence": [], "dataset": []}
    with open(osp.join(data_pth, "train.txt"), "r") as f:
        for line in f:
            sentence, label = line.strip().split("\t")
            train_dataset_dict["label"].append(float(label))
            train_dataset_dict["sentence"].append(sentence)
            train_dataset_dict["dataset"].append("meeting")
    eval_dataset_dict = {"label": [], "sentence": [], "dataset": []}
    with open(osp.join(data_pth, "dev.txt"), "r") as f:
        for line in f:
            sentence, label = line.strip().split("\t")
            eval_dataset_dict["label"].append(float(label))
            eval_dataset_dict["sentence"].append(sentence)
            eval_dataset_dict["dataset"].append("meeting")
    return train_dataset_dict, eval_dataset_dict
train_dataset_dict, eval_dataset_dict = load_local_data(data_pth)
train_dataset = MsDataset(Dataset.from_dict(train_dataset_dict)).to_hf_dataset()
eval_dataset = MsDataset(Dataset.from_dict(eval_dataset_dict)).to_hf_dataset()
print (train_dataset)

max_epochs = 5
lr = 2e-5
batch_size = 32
def cfg_modify_fn(cfg):
    cfg.task = Tasks.text_classification

    cfg.train.max_epochs = max_epochs
    cfg.train.optimizer.lr = lr
    cfg.train.dataloader = {
        "batch_size_per_gpu": batch_size,
        "workers_per_gpu": 1
    }

    cfg.evaluation.metrics = [Metrics.seq_cls_metric]
    cfg.train.lr_scheduler = {
        'type': 'LinearLR',
        'start_factor': 1.0,
        'end_factor': 0.0,
        'total_iters':
            int(len(train_dataset) / batch_size) * cfg.train.max_epochs,
        'options': {
            'by_epoch': False
        }
    }
    cfg.train.hooks[-1] = {
        'type': 'EvaluationHook',
        'by_epoch': True,
        'interval': 1
    }
    cfg['dataset'] = {
        'train': {
            'labels': ['否', '是', 'None'],
            'first_sequence': 'sentence',
            'label': 'label',
        }
    }
    return cfg

# map float to index
def map_labels(examples):
    map_dict = {0: "否", 1: "是"}
    examples['label'] = map_dict[int(examples['label'])]
    return examples

train_dataset = train_dataset.map(map_labels)
eval_dataset = eval_dataset.map(map_labels)

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


trainer = build_trainer(name='nlp-base-trainer', default_args=kwargs)

trainer.train()

# ---------------------------- Evaluation ---------------------------------

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)

# ---------------------------- Inference ---------------------------------
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from modelscope.outputs import OutputKeys

output_list = []
text_classification = pipeline(Tasks.text_classification, model=f'{WORK_DIR}/output')
with open(f'{data_pth}/dev.txt', "r") as f:
    for line in f:
        input_text = line.strip().split("\t")[0]
        output = text_classification(input_text)
        scores = output["scores"]
        if scores[1] > scores[2]:
            label = output["labels"][1]
        else:
            label = output["labels"][2]
        output_list.append(input_text + "\t" + label.replace("是", "1").replace("否", "0"))
with open(f'{WORK_DIR}/test_predict_result.txt', "w") as f:
    f.write("\n".join(output_list))