nltk中meteor_score的計算，報錯

懶得在介紹來龍去脈了，反正就是找到的代碼全是這種：

import nltk

hypothesis = ' '.join(['It', 'is', 'a', 'cat', 'at', 'room'])
reference = ' '.join(['It', 'is', 'a', 'cat', 'inside', 'the', 'room'])
#there may be several references
merteor_score = nltk.translate.meteor_score.single_meteor_score(reference, hypothesis)
print(merteor_score)

簡單來說就是hypothesis和reference都是字符串，然后我就一直報這個錯：TypeError: "hypothesis" expects pre-tokenized hypothesis (Iterable[str]): It is a cat at room。看起來是類型問題，然后找了一通，全都是用的字符串，最后沒辦法了看了眼源碼，說要求是{hypothesis}格式，我覺得應該是set類型吧，然后就把

hypothesis和reference改成了set，然后就可以了，就emmm，我還費勁巴拉改一晚上，難道是nltk版本更新所以數據格式換了？
改后代碼：

import nltk
# from nltk.corpus import wordnet
# nltk.download('wordnet')
hypothesis = ['It', 'is', 'a', 'cat', 'at', 'room']
reference = ['It', 'is', 'a', 'cat', 'inside', 'the', 'room']
hypothesis=set(hypothesis)
reference=set(reference)
#there may be several references
merteor_score = nltk.translate.meteor_score.single_meteor_score(reference, hypothesis)
print(merteor_score)