Closed trangtv57 closed 5 years ago
Yes, it is. The process is to segment the tokenized text into sentences first and then segment the sentences into words. To meet your need, you can write some simple snippet in Java or Python to process the output of the model. Cheers, T
I want just word segmentation my data, not split sentence by "." or other punctuation. But I don't know what's option for this. Or do you need sentence segmentation for word segmentation better ? Thanks you