Tree Transduction Tools for Cdec
We describe a collection of open source tools for learning tree-to-string and tree-to-tree transducers and the extensions to the cdec decoder that enable translation with these. Our modular, easy-to-extend tools extract rules from trees or forests aligned to strings and trees subject to different st...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Sciendo
2014-09-01
|
Series: | Prague Bulletin of Mathematical Linguistics |
Online Access: | https://doi.org/10.2478/pralin-2014-0011 |
id |
doaj-033711690e114f94a61081ca37339c33 |
---|---|
record_format |
Article |
spelling |
doaj-033711690e114f94a61081ca37339c332021-09-05T14:01:12ZengSciendoPrague Bulletin of Mathematical Linguistics 1804-04622014-09-011021273610.2478/pralin-2014-0011pralin-2014-0011Tree Transduction Tools for CdecAustin Matthews0Paul Baltescu1Phil Blunsom2Alon Lavie3Chris Dyer4Carnegie Mellon UniversityUniversity of OxfordUniversity of OxfordCarnegie Mellon UniversityCarnegie Mellon UniversityWe describe a collection of open source tools for learning tree-to-string and tree-to-tree transducers and the extensions to the cdec decoder that enable translation with these. Our modular, easy-to-extend tools extract rules from trees or forests aligned to strings and trees subject to different structural constraints. A fast, multithreaded implementation of the Cohn and Blunsom (2009) model for extracting compact tree-to-string rules is also included. The implementation of the tree composition algorithm used by cdec is described, and translation quality and decoding time results are presented. Our experimental results add to the body of evidence suggesting that tree transducers are a compelling option for translation, particularly when decoding speed and translation model size are important.https://doi.org/10.2478/pralin-2014-0011 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Austin Matthews Paul Baltescu Phil Blunsom Alon Lavie Chris Dyer |
spellingShingle |
Austin Matthews Paul Baltescu Phil Blunsom Alon Lavie Chris Dyer Tree Transduction Tools for Cdec Prague Bulletin of Mathematical Linguistics |
author_facet |
Austin Matthews Paul Baltescu Phil Blunsom Alon Lavie Chris Dyer |
author_sort |
Austin Matthews |
title |
Tree Transduction Tools for Cdec |
title_short |
Tree Transduction Tools for Cdec |
title_full |
Tree Transduction Tools for Cdec |
title_fullStr |
Tree Transduction Tools for Cdec |
title_full_unstemmed |
Tree Transduction Tools for Cdec |
title_sort |
tree transduction tools for cdec |
publisher |
Sciendo |
series |
Prague Bulletin of Mathematical Linguistics |
issn |
1804-0462 |
publishDate |
2014-09-01 |
description |
We describe a collection of open source tools for learning tree-to-string and tree-to-tree transducers and the extensions to the cdec decoder that enable translation with these. Our modular, easy-to-extend tools extract rules from trees or forests aligned to strings and trees subject to different structural constraints. A fast, multithreaded implementation of the Cohn and Blunsom (2009) model for extracting compact tree-to-string rules is also included. The implementation of the tree composition algorithm used by cdec is described, and translation quality and decoding time results are presented. Our experimental results add to the body of evidence suggesting that tree transducers are a compelling option for translation, particularly when decoding speed and translation model size are important. |
url |
https://doi.org/10.2478/pralin-2014-0011 |
work_keys_str_mv |
AT austinmatthews treetransductiontoolsforcdec AT paulbaltescu treetransductiontoolsforcdec AT philblunsom treetransductiontoolsforcdec AT alonlavie treetransductiontoolsforcdec AT chrisdyer treetransductiontoolsforcdec |
_version_ |
1717810571694309376 |