pdf = pdf def split_text(self, text: str) -> List[str]: if self.pdf: text = re.sub(r"\n{3,}", "\n", text) text = re.sub('\s', ' ', text) text = text.replace("\n\n", "") sent_sep_pattern = re.compile(

"""将时间机器数据集加载到文本行的列表中""" with open(d2l.download('time_machine'), 'r') as f: lines = f.readlines() return [re.sub('[^A-Za-z]+', ' ', line).strip().lower() for line in lines] lines = read_time_machine() print(f'# """将SNLI数据集解析为前提、假设和标签""" def extract_text(s): # 删除我们不会使用的信息 s = re.sub('\\(', '', s) s = re.sub('\\)', '', s) # 用一个空格替换两个或多个连续的空格 s = re.sub('\\s{2,}', ' ', s) return s.strip() label_set = {'entailment':