songyouwei / sa-dl Goto Github PK

Sentiment Analysis with Deep Learning models. Implemented with Tensorflow and Keras.

License: MIT License

Python 100.00%

sentiment-analysis nlp natural-language-processing machine-learning deep-learning tensorflow keras twitter-sentiment-analysis semeval attention-mechanism aspect-based-sentiment-analysis

sa-dl's Introduction

IMPORTANT

This repo is no longer maintained! Please go to: https://github.com/songyouwei/ABSA-PyTorch

SA-DL

Sentiment Analysis with Deep Learning models. Implemented with Tensorflow and Keras.

使用深度学习模型解决情感分析问题。

Dependencies

Tensorflow 1.7
Python 3.6
Pre-trained word vectors (See utils.py for more detail)
- Download pre-trained Twitter word vectors here,
- extract the glove.twitter.27B.zip and glove.42B.300d.zip to the root directory

An usage example

Training:

python ram.py

See the training process

tensorboard --logdir=./ram_logs

Reviews / Surveys

Zhang, Lei, Shuai Wang, and Bing Liu. "Deep Learning for Sentiment Analysis: A Survey." arXiv preprint arXiv:1801.07883 (2018). [pdf]

Young, Tom, et al. "Recent trends in deep learning based natural language processing." arXiv preprint arXiv:1708.02709 (2017). [pdf]

Papers & Models

RAM (ram.py)

Chen, Peng, et al. "Recurrent Attention Network on Memory for Aspect Sentiment Analysis." Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. 2017. [pdf]

MemNet (dmn.py)

Tang, Duyu, Bing Qin, and Ting Liu. "Aspect level sentiment classification with deep memory network." arXiv preprint arXiv:1605.08900 (2016). [pdf]

IAN

Ma, Dehong, et al. "Interactive Attention Networks for Aspect-Level Sentiment Classification." arXiv preprint arXiv:1709.00893 (2017).

TD-LSTM (td_lstm.py)

Tang, Duyu, et al. "Effective LSTMs for Target-Dependent Sentiment Classification." Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers. 2016. [pdf]

LSTM (lstm.py)

Licence

MIT License

sa-dl's People

Contributors

Stargazers

Watchers

Forkers

crystalmswang xxcharles shahnizam1 sayedali79 lazysjb jiaya12 gattuv mohammed-mustafa sahanduiuc erictham guoyin90 gokulsg swipswaps roopika-g

sa-dl's Issues

using predict function in td_lstm.py

i've tried your code for training purpose and its work really great. now im running this script to predict sentence. its throw me an error.

if __name__ == '__main__':
    # model = TDLSTM()
    # model.train()
    parser = argparse.ArgumentParser()
    parser.add_argument('-s', '--sentence', type=str, default=None, help='predict with sentence')
    args = parser.parse_args()
    model = TDLSTM()
    if args.sentence:
        model.predict(args.sentence) #"Obama is so kind and i love him"
    else:
        model.train()

by running python td_lstm.py -s "Obama is so kind and i love him" , throw error =

ValueError: Error when checking model input: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 2 array(s), but instead got the following list of 1 arrays: [array([[  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,
          0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,
          0,   0,   0,   0,   0,   0,   0,   0,   0, ...

thanks for your great works for creating this code. really helped me a lot 👍

Getting error - None values not supported when running ram.py

Here is the traceback:

Build model...
Traceback (most recent call last):
File "ram.py", line 117, in
model = RecurrentAttentionMemory()
File "ram.py", line 86, in init
x = shared_attention((memory, x))
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/keras/_impl/keras/engine/base_layer.py", line 239, in call
output = super(Layer, self).call(inputs, **kwargs)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/layers/base.py", line 714, in call
outputs = self.call(inputs, *args, **kwargs)
File "/Users/tushar/workspace/python/impact/songyouwei/SA-DL/attention_layer.py", line 66, in call
score *= K.cast(mask, K.floatx())
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/keras/_impl/keras/backend.py", line 1226, in cast
return math_ops.cast(x, dtype)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 779, in cast
x = ops.convert_to_tensor(x, name="x")
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 950, in convert_to_tensor
as_ref=False)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1040, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 1026, in _autopacking_conversion_function
return _autopacking_helper(v, inferred_dtype, name or "packed")
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 988, in _autopacking_helper
constant_op.constant(elem, dtype=dtype, name=str(i)))
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py", line 214, in constant
value, dtype=dtype, shape=shape, verify_shape=verify_shape))
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/tensor_util.py", line 421, in make_tensor_proto
raise ValueError("None values not supported.")
ValueError: None values not supported.

Is there something that needs fixing?