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...
Enregistré dans:
Auteurs principaux: | Franco Alberto Cardillo, Marcello Ferro, Claudia Marzi, Vito Pirrelli |
---|---|
Format: | article |
Langue: | EN |
Publié: |
Accademia University Press
2018
|
Sujets: | |
Accès en ligne: | https://doaj.org/article/ea47fdee18ca49449c2938cac6bdd45f |
Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
Documents similaires
-
For a Performance-oriented Notion of Regularity in Inflection: The Case of Modern Greek Conjugation
par: Stavros Bompolas, et autres
Publié: (2017) -
Using Deep Neural Networks for Smoothing Pitch Profiles in Connected Speech
par: Michele Ferro, et autres
Publié: (2019) -
Deep Learning for Automatic Image Captioning in Poor Training Conditions
par: Caterina Masotti, et autres
Publié: (2018) -
Multitask Learning with Deep Neural Networks for Community Question Answering
par: Daniele Bonadiman, et autres
Publié: (2017) -
Finding the Neural Net: Deep-learning Idiom Type Identification from Distributional Vectors
par: Yuri Bizzoni, et autres
Publié: (2018)