search

stanfordnlp / treelstm

Tree-structured Long Short-Term Memory networks (http://arxiv.org/abs/1503.00075)
GNU General Public License v2.0
875 stars 236 forks source link

sentiment classification task #7

Open csbwang opened 8 years ago

csbwang commented 8 years ago

dear sir, I found that the sentiment classification task use the file "STree.txt" during the preprocessing stage. Is it necessary and how to generate this file if i use my dataset?

sdrabb commented 7 years ago

i've got the same problem

lw081701019 commented 7 years ago

same problem

ryh95 commented 6 years ago

I think it is generated by constituency parsing, and you guys can check the preprocess-sick.py

guareniszhen commented 5 years ago

ryh95 is right. If you want to get the Chinese sequence. You can modify String PARSER_MODEL = "edu/stanford/nlp/models/parser/nndep/CTB_CoNLL_params.txt.gz" in file DependencyParser.java