possible typo?

[shawei3000]

trafficstars

    # fusion
    hh = tf.concat([h, h_B, h * h_B, h - h_B], axis=-1)
    x = tf.nn.relu(conv1d(uv, filters, 1, name='Wr'))           # (jim sha) should be hh?
    g = tf.nn.sigmoid(conv1d(hh, filters, 1, name='Wg'))

[ewrfcas]

@shawei3000 thanks for your correction

[shawei3000]

let me know if performance increases. with elmo, has potential to reach 84+ (FM)

[woshiyyya]

@ewrfcas Wow, did you write this model according to the paper by yourself? Or you are the author?

[ewrfcas]

@woshiyyya It is not a official version. I find that the earlier version of the paper can achieve better performance in the pytorch implement. Maybe I will verify the earlier version recently.

[doris-he]

Error: [E050] Can't find model 'en'. It doesn't seem to be a shortcut link, a Python package or a valid path to a data directory. preprocess.ipny

[ewrfcas]

@doris-he , this problem maybe caused by missing the spacy language package?