中文文本分类
将使用各种神经网络对文本进行分类,将有一个或者多个数据集对比
东方佑
世界500强企业,算法工程师,大模型设计,炼丹
展开
-
大话中文文本分类之TextRCNN
print("顶顶顶顶")原创 2020-10-01 21:30:19 · 562 阅读 · 0 评论 -
大话中文文本分类之Transformers
import torchimport torch.nn as nnimport torch.nn.functional as Fimport numpy as npimport copyclass Config(object): """配置参数""" def __init__(self, dataset, embedding): self.model_name = 'Transformer' self.train_path = dataset原创 2020-10-01 21:15:48 · 939 阅读 · 0 评论 -
大话中文文本分类之TextRNN_ATT
# coding: UTF-8import torchimport torch.nn as nnimport torch.nn.functional as Fimport numpy as npclass Config(object): """配置参数""" def __init__(self, dataset, embedding): self.model_name = 'TextRNN_Att' self.train_path = data原创 2020-10-01 21:13:39 · 641 阅读 · 0 评论 -
大话中文文本分类之TextRNN
# coding: UTF-8import torchimport torch.nn as nnimport numpy as npclass Config(object): """配置参数""" def __init__(self, dataset, embedding): self.model_name = 'TextRNN' self.train_path = dataset + '/data/train.txt'原创 2020-10-01 21:09:34 · 350 阅读 · 0 评论 -
大话中文文本分类之fastText
# coding: UTF-8import torchimport torch.nn as nnimport torch.nn.functional as Fimport numpy as npclass Config(object): """配置参数""" def __init__(self, dataset, embedding): self.model_name = 'FastText' self.train_path = dataset原创 2020-10-01 21:07:52 · 529 阅读 · 0 评论 -
大话中文文本分类之DPCNN
# coding: UTF-8import torchimport torch.nn as nnimport torch.nn.functional as Fimport numpy as npclass Config(object): """配置参数""" def __init__(self, dataset, embedding): self.model_name = 'DPCNN' self.train_path = dataset + '/原创 2020-10-01 21:06:00 · 519 阅读 · 0 评论 -
大话中文文本分类之textCNN
# coding: UTF-8import torchimport torch.nn as nnimport torch.nn.functional as Fimport numpy as npclass Config(object): """配置参数""" def __init__(self, dataset, embedding): self.model_name = 'TextCNN' self.train_path = dataset原创 2020-10-01 21:01:47 · 463 阅读 · 0 评论 -
大话中文文本分类之前数据处理
主要讲解一线文本编码和文本处理原创 2020-09-30 11:15:23 · 413 阅读 · 0 评论 -
textrank4zh来提取关键词和摘要
from textrank4zh import TextRank4Keyword, TextRank4Sentencetext="登记法搜我金佛我撒风景哦我阿萨德及覅偶按时间佛我爱上就发动我爱上就发动我按实际的佛那就是"tr4w = TextRank4Keyword()tr4w.analyze(text=text, lower=True, window=2)print( '关键词:' )for item in tr4w.get_keywords(20, word_min_len=1):原创 2020-09-30 10:51:43 · 749 阅读 · 0 评论 -
中文3d编码
b p m f d t n l g k h j q x zh ch sh r z c s y wa o e i u v ai ei ui ao ou iu ie ve er an en in un vn ang eng ing ong原创 2020-09-30 10:47:42 · 630 阅读 · 0 评论