Abstract Text segmentation is a fundamental task in natural language processing that comes in two levels of granularity: (i) segmenting a document into a sequence of topical segments (topic segmentation), and (ii) segmenting a sentence into a sequence of elementary discourse units (EDU segmentation). Traditional solutions to the two tasks heavily rely on carefully designed features. The recently proposed neural models do not need manual feature engineering, but they either suffer from sparse boundary tags or they cannot well handle the issue of variable size output vocabulary. We propose a generic end-to-end segmentation model called S EG B OT. S EG B OT uses a bidirectional recurrent neural network to encode input text sequence. The model then uses another recurrent neural network together with a pointer network to select text boundaries in the input sequence. In this way, S EG B OT does not require hand-crafted features. More importantly, our model inherently handles the issue of variable size output vocabulary and the issue of sparse boundary tags. In our experiments, S EG B OT outperforms state-of-the-art models on both topic and EDU segmentation tasks.