oaag's Introduction

OAAG

The code and data preparation is based on this repo.

Dataset

This is an benchmark dataset for opinion-aware answer generation in E-Commerce. You can downloaded the processed dataset via the following url:

https://drive.google.com/file/d/19012ClEam378QzPWL8ww8HMpBcjye_Rf/view?usp=sharing

Please cite the following paper if you use it in any way：

Yang Deng, Wenxuan Zhang, Wai Lam. Opinion-aware Answer Generation for Review-driven Question Answering in E-Commerce. In The 29th ACM International Conference on Information and Knowledge Management (CIKM 2020).

Also, because this benchmark is built from the Amazon QA datasets and Amazon review datasets provided by McAuley et al. (https://cseweb.ucsd.edu/~jmcauley/datasets.html), please also cite their papers following if you use the data:

Julian McAuley, Alex Yang. Addressing complex and subjective product-related queries with customer reviews. In World Wide Web (WWW), 2016.
R. He, J. McAuley. Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering. In World Wide Web (WWW), 2016.

Citation

If the data or code is used in your research, please star this repo and cite our paper as follows:

@inproceedings{DBLP:conf/cikm/DengZL20,
  author    = {Yang Deng and
               Wenxuan Zhang and
               Wai Lam},
  title     = {Opinion-aware Answer Generation for Review-driven Question Answering
               in E-Commerce},
  booktitle = {{CIKM} '20: The 29th {ACM} International Conference on Information
               and Knowledge Management, Virtual Event, Ireland, October 19-23, 2020},
  pages     = {255--264},
  year      = {2020},
  url       = {https://doi.org/10.1145/3340531.3411904},
}

oaag's People

Contributors

Stargazers

Watchers

oaag's Issues

ValueError: Shape must be rank 2 but is rank 3 for 'seq2seq/sentiment_layer/MatMul' (op: 'MatMul') with input shapes: [8,10,1029], [1029,256].

Hi, thanks for offering your implement for the OAAG model.

I got this error while running it:

Traceback (most recent call last):
  File "/code/oaag-static/run_summarization.py", line 347, in <module>
    tf.compat.v1.app.run()
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/platform/app.py", line 125, in run
    _sys.exit(main(argv))
  File "/code/oaag-static/run_summarization.py", line 336, in main
    setup_training(model, batcher, vocab, hps)
  File "/code/oaag-static/run_summarization.py", line 163, in setup_training
    model.build_graph() # build the graph
  File "/code/oaag-static/model.py", line 480, in build_graph
    self._add_seq2seq()
  File "/code/oaag-static/model.py", line 372, in _add_seq2seq
    self.y_prob, self.y_pred, self.review_attention, decode_in_state = self._self_matching(sentiment_input, hps.batch_size)

  File "/code/oaag-static/model.py", line 292, in _self_matching
    U = tf.tanh(tf.matmul(sentiment_input, W))

  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/math_ops.py", line 2455, in matmul
    a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/gen_math_ops.py", line 5333, in mat_mul
    name=name)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper
    op_def=op_def)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py", line 3300, in create_op
    op_def=op_def)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py", line 1823, in __init__
    control_input_ops)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py", line 1662, in _create_c_op
    raise ValueError(str(e))
ValueError: Shape must be rank 2 but is rank 3 for 'seq2seq/sentiment_layer/MatMul' (op: 'MatMul') with input shapes: [8,10,1029], [1029,256].

It seems that the sentiment_input and W are not at the same shape, could you please tell me how to fix it?