Skip to content
Snippets Groups Projects
Unverified Commit 2236ae82 authored by aaa123git's avatar aaa123git Committed by GitHub
Browse files

fix bug. replace 'id' with 'ID' (#198)

parent a067adb8
Branches
No related tags found
No related merge requests found
Show whitespace changes
Inline Side-by-side
convlab2/nlu/jointBERT/multiwoz/nlu.py
+ 3
− 0
View file @ 2236ae82
import os import os
import re
import zipfile import zipfile
import json import json
import torch import torch
...@@ -66,6 +67,8 @@ class BERTNLU(NLU): ...@@ -66,6 +67,8 @@ class BERTNLU(NLU):
print("BERTNLU loaded") print("BERTNLU loaded")
def predict(self, utterance, context=list()): def predict(self, utterance, context=list()):
# Note: spacy cannot tokenize 'id' or 'Id' correctly.
utterance = re.sub(r'\b(id|Id)\b', 'ID', utterance)
# tokenization first, very important! # tokenization first, very important!
ori_word_seq = [token.text for token in self.nlp(unidecode(utterance)) if token.text.strip()] ori_word_seq = [token.text for token in self.nlp(unidecode(utterance)) if token.text.strip()]
# print(ori_word_seq) # print(ori_word_seq)
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment