Unlabeled Data for Morphological Generation With Character-Based Sequence-to-Sequence Models

05/17/2017
by   Katharina Kann, et al.
0

We present a semi-supervised way of training a character-based encoder-decoder recurrent neural network for morphological reinflection, the task of generating one inflected word form from another. This is achieved by using unlabeled tokens or random strings as training data for an autoencoding task, adapting a network for morphological reinflection, and performing multi-task training. We thus use limited labeled data more effectively, obtaining up to 9.9 different languages.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/18/2015

Morphological Inflection Generation Using Character Sequence to Sequence Learning

Morphological inflection generation is the task of generating the inflec...
research
04/06/2017

Multi-space Variational Encoder-Decoders for Semi-supervised Labeled Sequence Transduction

Labeled sequence transduction is a task of transforming one sequence int...
research
06/27/2017

CoNLL-SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection in 52 Languages

The CoNLL-SIGMORPHON 2017 shared task on supervised morphological genera...
research
04/17/2021

Minimal Supervision for Morphological Inflection

Neural models for the various flavours of morphological inflection tasks...
research
12/19/2016

Neural Multi-Source Morphological Reinflection

We explore the task of multi-source morphological reinflection, which ge...
research
12/08/2020

The Role of Interpretable Patterns in Deep Learning for Morphology

We examine the role of character patterns in three tasks: morphological ...
research
05/26/2023

An Investigation of Noise in Morphological Inflection

With a growing focus on morphological inflection systems for languages w...

Please sign up or login with your details

Forgot password? Click here to reset