I have an NLTextClassifier, trained in English. When asked to classify texts in Chinese, it appears to be significantly slower than when classifying texts in English.
Is this in fact the case? I expected the classification to be O(n) in the length of the text to be classified, and for runtime to be independent of language.
How much performance difference ? Factor of 2 ? Much more ?
Which framework do you use ?
I would not be suprised there are differences between languages. Some may require more complex analysis.
more like an order of magnitude.
But the neural network is the network; why would it run more slowly on garbage input than on any other input?