Closed JuanFF closed 4 years ago
For this, I would keep both the examples in training set and let the model learn the good morning
(or contextually similarly phrases) should not be split when accompanied by phrases like I need help to fix this issue
.
So, keep both example 1 and example 2 in training set and train the model. Based on your results (i.e: if it segments sentences like 1), you might need to add more data similar to example 1.
Thanks a lot!
@JuanFF I am closing the issue for now. Feel free to re-open if required.
Hello,
I'm going to expand a custom training set with new examples. These two sentences are in the set:
In this case, I need that DeepSegment keeps the boundaries of the longest one (1). Considering that both examples are in training, I wonder if the final result would be
['Good morning', 'I need help to fix this issue']
I would like to avoid this but keep both examples as training. Would this be possible after training the model?
Thanks