Char-RNN and Active Learning for Hashtag Segmentation

11/08/2019
by   Taisiya Glushkova, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/13/2021

Depth Uncertainty Networks for Active Learning

In active learning, the size and complexity of the training dataset chan...
research
01/07/2021

Diminishing Uncertainty within the Training Pool: Active Learning for Medical Image Segmentation

Active learning is a unique abstraction of machine learning techniques w...
research
12/13/2022

ALRt: An Active Learning Framework for Irregularly Sampled Temporal Data

Sepsis is a deadly condition affecting many patients in the hospital. Re...
research
05/07/2020

Deeply Supervised Active Learning for Finger Bones Segmentation

Segmentation is a prerequisite yet challenging task for medical image an...
research
07/12/2018

How transferable are the datasets collected by active learners?

Active learning is a widely-used training strategy for maximizing predic...
research
09/21/2022

Is More Data Better? Re-thinking the Importance of Efficiency in Abusive Language Detection with Transformers-Based Active Learning

Annotating abusive language is expensive, logistically complex and creat...
research
08/15/2018

Using Regular Languages to Explore the Representational Capacity of Recurrent Neural Architectures

The presence of Long Distance Dependencies (LDDs) in sequential data pos...

Please sign up or login with your details

Forgot password? Click here to reset