Qi Liu

Hi: Thanks for your email. Yes. I am using OSX wheel. I fixed that problem by replacing the model sentence to this one model = Doc2Vec(min_count=1, window=10, size=5, sample=1e-4, negative=5,...

I also faced this issue. May I ask whether there is any easy workaround to increase the model parallel or pipeline parallel sizes? Thanks!

Hi Jasmine: Thank you for your issue. The datasets can be downloaded from https://www.cs.jhu.edu/˜mdredze/datasets/sentiment/ https://www.cs.cornell.edu/people/pabo/movie-review-data/ http://www.cs.uic.edu/˜liub/FBS/sentiment-analysis.html Let me know if there is any problem for preprocessing. Thanks! Best Regards, Qi

Hi: The link seems broken. Please find the datasets in these two links, which are still available: https://www.cs.uic.edu/~liub/FBS/sentiment-analysis.html#datasets https://www.cs.jhu.edu/~mdredze/data/ Thanks! Best Regards, Qi

Hi Steffen: Thank you very much for your two suggestions. :) Sorry for the late reply. I have updated the README to reflect suggestion 1. For suggestion 2, I do...

Hi Steffen: The sparse_softmax_cross_entropy_with_logits can work with multi-class case. I found a problem in my code (I hardcode binary class (i.e. 2) when generating the logits for sparse_softmax_cross_entropy_with_logits). I add...

Hi Steffen: Thank you very much for your advice. I have a domain-agnostic version (multi_view.py) with repeated code as the domain-aware version. I don't have the chance to clean it...

Hi Steffen: I modified the code from other's code. It is a historical problem. Just set num_steps = maxlen will solve the problem. Sorry for the confusion caused. Thanks! Best...

一般输入是不分句的，可以保持顺序信息。如果分句的话，要考虑一些方法来维持句子的关系或者顺序信息，可以参考 (https://www.aclweb.org/anthology/N16-1174.pdf).

这里的句子状态是说的输入的sequence，是指整个的输入，不是针对每个句子的。所以一个输入只有一个状态。可能论文说的sentence-state有点误解。