peace195 / aspect-based-sentiment-analysis Goto Github PK
View Code? Open in Web Editor NEWAspect Based Sentiment Analysis
Home Page: https://peace195.github.io/choose-distinct-units-in-lstm/
License: GNU General Public License v3.0
Aspect Based Sentiment Analysis
Home Page: https://peace195.github.io/choose-distinct-units-in-lstm/
License: GNU General Public License v3.0
How did you obtain the sentiment embedding (sswe-u.txt)? I can't seem to find anything about it in the README, and the file isn't explained in the drive either. I am trying to replicate the results on a different language, so evidently I need to retrain the sentiment embeddings.
Also, how did you acquire the incremental/decremental/negative/positive/reverse/stop words?
Hi, why do you use
sentiment = tf.multiply(sentiment, tf.expand_dims(self.tf_X_binary_mask, 2))
on line 178 in sa_aspect_oop.py
? It seems highly influential on the results, and I wonder if it is right, since it seems to use the ground truth in the prediction?
Environment:
python 2.7.13 (Anaconda)
tensorflow0.12.1
and I got this error:
Traceback (most recent call last):
File "/root/PycharmProjects/aspect-based-sentiment-analysis/code/sa_aspect_oop.py", line 392, in
main()
File "/root/PycharmProjects/aspect-based-sentiment-analysis/code/sa_aspect_oop.py", line 383, in main
model.modeling()
File "/root/PycharmProjects/aspect-based-sentiment-analysis/code/sa_aspect_oop.py", line 146, in modeling
X_train = tf.concat([self.tf_X_train, X_sent_for_word], 2)
File "/root/.pyenv/versions/anaconda2-5.0.0/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 1075, in concat
dtype=dtypes.int32).get_shape(
File "/root/.pyenv/versions/anaconda2-5.0.0/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 669, in convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/root/.pyenv/versions/anaconda2-5.0.0/lib/python2.7/site-packages/tensorflow/python/framework/constant_op.py", line 176, in _constant_tensor_conversion_function
return constant(v, dtype=dtype, name=name)
File "/root/.pyenv/versions/anaconda2-5.0.0/lib/python2.7/site-packages/tensorflow/python/framework/constant_op.py", line 165, in constant
tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape, verify_shape=verify_shape))
File "/root/.pyenv/versions/anaconda2-5.0.0/lib/python2.7/site-packages/tensorflow/python/framework/tensor_util.py", line 367, in make_tensor_proto
_AssertCompatible(values, dtype)
File "/root/.pyenv/versions/anaconda2-5.0.0/lib/python2.7/site-packages/tensorflow/python/framework/tensor_util.py", line 302, in _AssertCompatible
(dtype.name, repr(mismatch), type(mismatch).name))
TypeError: Expected int32, got list containing Tensors of type '_Message' instead.
Should I change the version of TensorFlow? THANKS
I'm really hoping that you can reshare your embedding result. Thank you a bunch!
Hi,
How to create 'Restaurants_corpus_for_word2vec.txt' file?
Thanks.
mldl@ub1604:/ub16_prj/aspect-based-sentiment-analysis/code$ python sa_aspect_oop.py/ub16_prj/aspect-based-sentiment-analysis/code$
Traceback (most recent call last):
File "sa_aspect_oop.py", line 15, in
import utils
File "/home/mldl/ub16_prj/aspect-based-sentiment-analysis/code/utils.py", line 30
continue
SyntaxError: 'continue' not properly in loop
mldl@ub1604:
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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. 📊📈🎉
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 ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.