添加词之后出现的报错

[Jing-XING]

对于ltp4.2.0，在使用add_words之后特殊情况下的报错。直觉上是添加了word（如‘abc'）之后，输入类似”xabc“这样的词会出现这样的问题：
输入

ltp.add_words(['800000股'])
ltp.pipeline(['3800000股'], tasks=["cws", "pos"])

报错信息为KeyError

Traceback (most recent call last)
Cell In[57], line 1
----> 1 ltp.pipeline(['3800000股'], tasks=["cws", "pos"])

File D:\software\anaconda\envs\EDEE\lib\site-packages\ltp\nerual.py:24, in no_grad.<locals>.wrapper(*args, **kwargs)
     22 def wrapper(*args, **kwargs):
     23     with torch.no_grad():
---> 24         return func(*args, **kwargs)

File D:\software\anaconda\envs\EDEE\lib\site-packages\ltp\nerual.py:185, in LTP.pipeline(self, inputs, tasks, raw_format, return_dict)
    183         cache[cache_key] = (hidden_state, attention_mask)
    184     result = self.model.task_heads[task](hidden_state, attention_mask)
--> 185     store[task] = self.post[task](result, hidden, store, inputs, tokenized)
    187 if not raw_format:
    188     if is_split_into_words:

File D:\software\anaconda\envs\EDEE\lib\site-packages\ltp\nerual.py:24, in no_grad.<locals>.wrapper(*args, **kwargs)
     22 def wrapper(*args, **kwargs):
     23     with torch.no_grad():
---> 24         return func(*args, **kwargs)

File D:\software\anaconda\envs\EDEE\lib\site-packages\ltp\nerual.py:293, in LTP._cws_post(self, result, hidden, store, inputs, tokenized)
    291 for i, e in enumerate(word_end):
    292     if i == 0:
--> 293         entities[-1].append((0, length2index[e]))
    294     else:
    295         entities[-1].append((length2index[word_end[i - 1]] + 1, length2index[e]))

KeyError: 1