在Python中使用Textblob進行Lemmatize

Question

我已經編寫了使用文本blob在Python中使句子定理的代碼，但沒有得到預期的結果：

def get_lemmatize_text(transcript):
    transcript = transcript.strip()
    blob = TextBlob(transcript)
    for word in blob:
        expected_str = Word(word)
        expected_str = expected_str.lemmatize()
    return expected_str
print(get_lemmatize_text("he had not received the four letters we d sent him as he had been travelling for the whole of august and hadn t received any call or text from us . he has just arrived today and has called us straight away . he has also just of his account when he had asked for it to be cancelled before it switched from the first additions datestr . he says he received contact from us that we were looking into this but doesnot have that to hand"))

我得到以下輸出： d

出了什么問題？ 誰能幫助我或糾正我？

Answer 1

您的代碼將句子作為字符明智的.split()迭代將解決該問題。 那么您就不會保留您的結果，這就是為什么要獲取上一個迭代list追加的結果會解決這一問題的原因。 如果您解決了這兩個問題，您的代碼將可以正常工作:)嘗試執行此操作，

   blob = TextBlob(transcript).split()
   result=[]
   for word in blob:
        expected_str = Word(word)
        expected_str = expected_str.lemmatize()
        result.append(expected_str)
   return result #or try this return ' '.join(result)