I actually tried to implement this modules to English texts, and results are generated. But the description of the bilstm module is to sentiment the "Chinese" words, is it correct to sentiment the "English" words?

PaddlePaddle / PaddleHub

Awesome pre-trained models toolkit based on PaddlePaddle. (400+ models including Image, Text, Audio, Video and Cross-Modal with Easy Inference & Serving)【安全加固，暂停交互，请耐心等待】

https://www.paddlepaddle.org.cn/hub

Apache License 2.0

12.73k stars 2.08k forks source link

I actually tried to implement this modules to English texts, and results are generated. But the description of the bilstm module is to sentiment the "Chinese" words, is it correct to sentiment the "English" words? #1848

Open crjhonor opened 2 years ago

crjhonor commented 2 years ago

I actually tried to implement this modules to English texts, and results are generated. But the description of the bilstm module is to sentiment the "Chinese" words, is it correct to sentiment the "English" words?

Originally posted by @crjhonor in https://github.com/PaddlePaddle/PaddleHub/discussions/1847

KPatr1ck commented 2 years ago

Hi, I think the module you mentioned is senta_bilstm. This module is a pretrained model based on Chinese corpus, so it is unable to handle English sentences.

I suggest that you can use models like roberta_skep_large_en in https://github.com/baidu/Senta for English-language sentiment analysis.