Words splitting instead of sentence splitting. Is this a bug?

In https://github.com/ChenRocks/fast_abs_rl/blob/master/make_extraction_labels.py#L47 you split articles and abstracts into sentences to compute the labels for extraction. However `t.split()` splits into words, and not sentences. Is this a bug? If not, how does it work?

Start at make_extraction_labels.py#L47 and trace how t.split() is used while computing extraction labels for articles and abstracts. Compare the expected sentence-level inputs with the actual behavior, then determine whether this is intentional or a bug; done means the behavior is explained or the issue is narrowed to a specific correction.

Written by the indexing model from the issue text.