Models for Inuktitut-English Word Alignment
This paper presents a set of techniques for bitext word alignment, optimized for a language pair with the characteristics of Inuktitut-English. The resulting systems exploit cross-lingual affinities at the sublexical level of syllables and substrings, as well as regular patterns of transliteration a...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Text |
Language: | English |
Published: |
2005
|
Subjects: | |
Online Access: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.8482 http://acl.ldc.upenn.edu/W/W05/W05-0811.pdf |
id |
ftciteseerx:oai:CiteSeerX.psu:10.1.1.59.8482 |
---|---|
record_format |
openpolar |
spelling |
ftciteseerx:oai:CiteSeerX.psu:10.1.1.59.8482 2023-05-15T16:55:34+02:00 Models for Inuktitut-English Word Alignment Charles Schafer Elliott Franco Drabek The Pennsylvania State University CiteSeerX Archives 2005 application/pdf http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.8482 http://acl.ldc.upenn.edu/W/W05/W05-0811.pdf en eng http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.8482 http://acl.ldc.upenn.edu/W/W05/W05-0811.pdf Metadata may be used without restrictions as long as the oai identifier remains attached to it. http://acl.ldc.upenn.edu/W/W05/W05-0811.pdf text 2005 ftciteseerx 2016-01-08T13:28:21Z This paper presents a set of techniques for bitext word alignment, optimized for a language pair with the characteristics of Inuktitut-English. The resulting systems exploit cross-lingual affinities at the sublexical level of syllables and substrings, as well as regular patterns of transliteration and the tendency towards monotonicity of alignment. Our most successful systems were based on classifier combination, and we found different combination methods performed best under the target evaluation metrics of F-measure and alignment error rate. Text inuktitut Unknown |
institution |
Open Polar |
collection |
Unknown |
op_collection_id |
ftciteseerx |
language |
English |
description |
This paper presents a set of techniques for bitext word alignment, optimized for a language pair with the characteristics of Inuktitut-English. The resulting systems exploit cross-lingual affinities at the sublexical level of syllables and substrings, as well as regular patterns of transliteration and the tendency towards monotonicity of alignment. Our most successful systems were based on classifier combination, and we found different combination methods performed best under the target evaluation metrics of F-measure and alignment error rate. |
author2 |
The Pennsylvania State University CiteSeerX Archives |
format |
Text |
author |
Charles Schafer Elliott Franco Drabek |
spellingShingle |
Charles Schafer Elliott Franco Drabek Models for Inuktitut-English Word Alignment |
author_facet |
Charles Schafer Elliott Franco Drabek |
author_sort |
Charles Schafer |
title |
Models for Inuktitut-English Word Alignment |
title_short |
Models for Inuktitut-English Word Alignment |
title_full |
Models for Inuktitut-English Word Alignment |
title_fullStr |
Models for Inuktitut-English Word Alignment |
title_full_unstemmed |
Models for Inuktitut-English Word Alignment |
title_sort |
models for inuktitut-english word alignment |
publishDate |
2005 |
url |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.8482 http://acl.ldc.upenn.edu/W/W05/W05-0811.pdf |
genre |
inuktitut |
genre_facet |
inuktitut |
op_source |
http://acl.ldc.upenn.edu/W/W05/W05-0811.pdf |
op_relation |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.8482 http://acl.ldc.upenn.edu/W/W05/W05-0811.pdf |
op_rights |
Metadata may be used without restrictions as long as the oai identifier remains attached to it. |
_version_ |
1766046569524625408 |