Deep Learning of Inflection and the Cell-Filling Problem
Machine learning offers two basic strategies for morphology induction: lexical segmentation and surface word relation. The first approach assumes that words can be segmented into morphemes. Inferring a novel inflected form requires identification of morphemic constituents and a strategy for their re...
Saved in:
Main Authors: | Franco Alberto Cardillo, Marcello Ferro, Claudia Marzi, Vito Pirrelli |
---|---|
Format: | article |
Language: | EN |
Published: |
Accademia University Press
2018
|
Subjects: | |
Online Access: | https://doaj.org/article/ea47fdee18ca49449c2938cac6bdd45f |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
For a Performance-oriented Notion of Regularity in Inflection: The Case of Modern Greek Conjugation
by: Stavros Bompolas, et al.
Published: (2017) -
Using Deep Neural Networks for Smoothing Pitch Profiles in Connected Speech
by: Michele Ferro, et al.
Published: (2019) -
Deep Learning for Automatic Image Captioning in Poor Training Conditions
by: Caterina Masotti, et al.
Published: (2018) -
Multitask Learning with Deep Neural Networks for Community Question Answering
by: Daniele Bonadiman, et al.
Published: (2017) -
Finding the Neural Net: Deep-learning Idiom Type Identification from Distributional Vectors
by: Yuri Bizzoni, et al.
Published: (2018)