在运行LSTM sentiment analysis 代码中遇到如下报错信息:
WARNING: No known abbreviations for language 'en', attempting fall-back to English version...
ERROR: No abbreviations files found in .../nonbreaking_prefixes
Tokenizing.. Done
原因是tokenizer.perl中的nonbreaking_prefixes.en没有找到。在代码所在路径中创建文件夹 nonbreaking_prefixes ,然后从
https://github.com/moses-smt/mosesdecoder/tree/master/scripts/share/nonbreaking_prefixes 中下载所需文件到该新建文件夹即可。