Unsupervised Learning of Morphology for English and Inuktitut
We describe a simple unsupervised technique for learning morphology by identifying hubs in an automaton. For our purposes, a hub is a node in a graph with in-degree greater than one and out-degree greater than one. We create a word-trie, transform it into a minimal DFA, then identify hubs. Those hub...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Text |
Language: | English |
Published: |
2003
|
Subjects: | |
Online Access: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.4.8011 http://acl.ldc.upenn.edu/N/N03/N03-2015.pdf |
id |
ftciteseerx:oai:CiteSeerX.psu:10.1.1.4.8011 |
---|---|
record_format |
openpolar |
spelling |
ftciteseerx:oai:CiteSeerX.psu:10.1.1.4.8011 2023-05-15T16:55:35+02:00 Unsupervised Learning of Morphology for English and Inuktitut Howard Johnson Joel Martin The Pennsylvania State University CiteSeerX Archives 2003 application/pdf http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.4.8011 http://acl.ldc.upenn.edu/N/N03/N03-2015.pdf en eng http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.4.8011 http://acl.ldc.upenn.edu/N/N03/N03-2015.pdf Metadata may be used without restrictions as long as the oai identifier remains attached to it. http://acl.ldc.upenn.edu/N/N03/N03-2015.pdf text 2003 ftciteseerx 2021-10-24T00:21:09Z We describe a simple unsupervised technique for learning morphology by identifying hubs in an automaton. For our purposes, a hub is a node in a graph with in-degree greater than one and out-degree greater than one. We create a word-trie, transform it into a minimal DFA, then identify hubs. Those hubs mark the boundary between root and suffix, achieving similar performance to more complex mixtures of techniques. Text inuktitut Unknown |
institution |
Open Polar |
collection |
Unknown |
op_collection_id |
ftciteseerx |
language |
English |
description |
We describe a simple unsupervised technique for learning morphology by identifying hubs in an automaton. For our purposes, a hub is a node in a graph with in-degree greater than one and out-degree greater than one. We create a word-trie, transform it into a minimal DFA, then identify hubs. Those hubs mark the boundary between root and suffix, achieving similar performance to more complex mixtures of techniques. |
author2 |
The Pennsylvania State University CiteSeerX Archives |
format |
Text |
author |
Howard Johnson Joel Martin |
spellingShingle |
Howard Johnson Joel Martin Unsupervised Learning of Morphology for English and Inuktitut |
author_facet |
Howard Johnson Joel Martin |
author_sort |
Howard Johnson |
title |
Unsupervised Learning of Morphology for English and Inuktitut |
title_short |
Unsupervised Learning of Morphology for English and Inuktitut |
title_full |
Unsupervised Learning of Morphology for English and Inuktitut |
title_fullStr |
Unsupervised Learning of Morphology for English and Inuktitut |
title_full_unstemmed |
Unsupervised Learning of Morphology for English and Inuktitut |
title_sort |
unsupervised learning of morphology for english and inuktitut |
publishDate |
2003 |
url |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.4.8011 http://acl.ldc.upenn.edu/N/N03/N03-2015.pdf |
genre |
inuktitut |
genre_facet |
inuktitut |
op_source |
http://acl.ldc.upenn.edu/N/N03/N03-2015.pdf |
op_relation |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.4.8011 http://acl.ldc.upenn.edu/N/N03/N03-2015.pdf |
op_rights |
Metadata may be used without restrictions as long as the oai identifier remains attached to it. |
_version_ |
1766046579647578112 |