# Char-RNN and Active Learning for Hashtag Segmentation

arXiv: https://arxiv.org/abs/1911.03270 · HTML: https://mlsanity.com/paper/1911.03270/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2019.

## Built on by (most cited first, 1 of 1)

- [ALRt: An Active Learning Framework for Irregularly Sampled Temporal Data](https://mlsanity.com/paper/2212.06364/) (2022)

## Abstract (arXiv)

We explore the abilities of character recurrent neural network (char-RNN) for hashtag segmentation. Our approach to the task is the following: we generate synthetic training dataset according to frequent n-grams that satisfy predefined morpho-syntactic patterns to avoid any manual annotation. The active learning strategy limits the training dataset and selects informative training subset. The approach does not require any language-specific settings and is compared for two languages, which differ in inflection degree.