zixuanke / lifelongsentclass Goto Github PK
View Code? Open in Web Editor NEWCode for ECML/PKDD 2020 Paper --- Continual Learning with Knowledge Transfer for Sentiment Classification
Code for ECML/PKDD 2020 Paper --- Continual Learning with Knowledge Transfer for Sentiment Classification
Is it convenient for you to open the complete data set mentioned in the paper? I hope to continue the study in this direction, I would be very grateful if the dataset is available.
Thanks for your great work! It seems something is wrong with your source code. I run the script and it turns out like below.
Traceback (most recent call last):
File "run.py", line 134, in <module>
appr.train(task,train_dataloader,valid_dataloader,args)
File "/root/autodl-tmp/LifelongSentClass-master/approaches/bert_rnn_kan_ncl.py", line 81, in train
self.train_epoch(t,train,iter_bar,which_type)
File "/root/autodl-tmp/LifelongSentClass-master/approaches/bert_rnn_kan_ncl.py", line 126, in train_epoch
outputs=self.model.forward(task,input_ids, segment_ids, input_mask,which_type,s)
File "/root/autodl-tmp/LifelongSentClass-master/networks/bert_gru_kan.py", line 45, in forward
mcl_output,mcl_hidden = self.mcl.gru(sequence_output)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/root/autodl-tmp/LifelongSentClass-master/networks/bert_gru_kan.py", line 125, in forward
output, hidden = self.rnn(x)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/rnn.py", line 913, in forward
is_batched = input.dim() == 3
AttributeError: 'str' object has no attribute 'dim'
Hello, I'm wondering why you've chosen RNN as the main CL network? Did you try other networks such as MLP or CNN - what was the performance difference you observed?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.