dc.contributor.author | Jónsson, Haukur Páll |
dc.contributor.author | Loftsson, Hrafn |
dc.contributor.author | Steingrímsson, Steinþór |
dc.date.accessioned | 2020-06-24T14:40:46Z |
dc.date.available | 2020-06-24T14:40:46Z |
dc.date.issued | 2020-06-23 |
dc.identifier.uri | http://hdl.handle.net/20.500.12537/46 |
dc.description | Moses phrase-based statistical machine translation (Moses PBSMT) is a system which is used to develop and run machine translation models. It is distributed here as four packages: 1. Code from a github repository to train and run models. 2. Pretrained is-en system (Docker) 3. Pretrained en-is system (Docker) 4. Frontend to pre- and postprocess text for translation (Docker) The models here are not (exactly) the same as were used for human evaluation. These models have additionally been trained on open dictionaries to extend their vocabularies. Moses phrase-based statistical machine translation (Moses PBSMT) er kerfi til þess að þróa og keyra tölfræðilegar vélþýðingar. Hér er dreift fjórum pökkum: 1. Kóða af github geymslusvæði fyrir þjálfun og keyrslu á líkönum 2. Forþjálfuðu is-en vélþýðingarlíkani (Docker) 3. Forþjálfuðu en-is vélþýðingarlíkani (Docker) 4. Framenda til að for- og eftirvinna texta fyrir þýðingar (Docker) Líkönin sem eru sett hér eru ekki (nákvæmlega) þau sömu og voru notuð við mannlegt mat. Þessi líkön hafa aukalega verið þjálfuð á gögnum úr opnum orðabókum til þess að auka orðaforða. |
dc.language.iso | isl |
dc.language.iso | eng |
dc.publisher | Reykjavik University |
dc.rights | The MIT License (MIT) |
dc.rights.uri | https://opensource.org/licenses/mit-license.php |
dc.rights.label | PUB |
dc.source.uri | https://github.com/cadia-lvl/SMT |
dc.subject | machine translation |
dc.subject | statistical machine translation |
dc.subject | moses |
dc.title | MT: Moses-SMT (1.0) |
dc.type | toolService |
metashare.ResourceInfo#ContentInfo.detailedType | service |
metashare.ResourceInfo#ResourceComponentType#ToolServiceInfo.languageDependent | true |
has.files | yes |
branding | Clarin IS Repository |
demo.uri | https://nlp.cs.ru.is/moses/translateText |
contact.person | Haukur Páll Jónsson haukurpj@ru.is Reykjavik University |
sponsor | Ministry of Education, Science and Culture (Mennta- og menningamálaráðuneytið) Language Technology for Icelandic 2019-2023 Machine Translation - baseline (V3) nationalFunds |
files.size | 11789798918 |
files.count | 4 |
Files in this item
Download all files in item (10.98 GB)- Name
- SMT-master.zip
- Size
- 25.3 MB
- Format
- application/zip
- Description
- GitHub repository snapshot
- MD5
- 9f33d407dd2f9d6174587513b07e0fed
- SMT-master
- README.md4 kB
- .gitignore149 B
- preprocessing
- README.md1 kB
- tests
- test_api.py184 B
- list_merging.py1 kB
- serialization.py1 kB
- test_read_rmh.py526 B
- memory_footprint.py304 B
- test_pipeline.py1 kB
- docker-build.sh164 B
- preprocessing
- client.py750 B
- file_handler.py4 kB
- types.py470 B
- api.py5 kB
- __init__.py0 B
- server.py3 kB
- pipeline.py13 kB
- resources
- truecase-model.en13 MB
- truecase-model.is34 MB
- __init__.py0 B
- tok.is7 MB
- conftest.py0 B
- requirements.txt1 kB
- Dockerfile283 B
- main.py9 kB
- LICENSE1 kB
- scripts
- README.md842 B
- run_in_singularity.sh764 B
- 2preprocess
- preprocess.sh2 kB
- lm.sh871 B
- 1format
- extract_dicts.sh1 kB
- en_mono_format.py4 kB
- environment.sh1 kB
- 4package
- docker-build.sh543 B
- README.md1 kB
- docker-run.sh117 B
- Dockerfile55 B
- 3train
- dict.sh4 kB
- evaluate.sh514 B
- translate.sh507 B
- end_to_end.sh5 kB
- experiments
- unkown_tokens.sh1 kB
- data
- readme.md1 kB
- raw
- parice32 B
- en_mono39 B
- rmh37 B
- dictionary
- wiki.tsv1 MB
- manual.tsv27 B
- apertium-isl-eng.isl-eng.dix2 MB
- out23 B
- formatted30 B
- moses
- docker-build.sh106 B
- README.md2 kB
- Dockerfile1 kB
- docker-compose.yml617 B
- LICENSE1 kB
- notebooks
- ParIce - 2. filter.ipynb174 kB
- Moses xmlrpc.ipynb1 kB
- README.md880 B
- Moses hand-calculation.ipynb1 kB
- google_translate.ipynb9 kB
- data_exploration.ipynb383 kB
- explore-results.ipynb170 kB
- ParIce - 1. format.ipynb42 kB
- Name
- moses-lvl.tar.gz
- Size
- 493.84 MB
- Format
- application/gzip
- Description
- Frontend for translations
- MD5
- 4dfcbb6b3b46a84768a6ca47799e05ae
- 4344bf7b79d16de38871fb8ee7fe177b126da26d40430fdfbb234931c9e9f95b
- json477 B
- VERSION3 B
- layer.tar4 kB
- f0c15c5ba6e85e992ef5f561002cd3a6037d0d79ba9021795013ca1316a9a997
- json477 B
- VERSION3 B
- layer.tar17 MB
- fdafbbcf2b07a4c8717ff019312cabc2b09134d6f776d16f1e8c975213fd2486
- json477 B
- VERSION3 B
- layer.tar496 MB
- d6270abdf0c46e4907d84186d44c52887e838da108f5a4039ac2cd7b9c2b60f5
- json401 B
- VERSION3 B
- layer.tar113 MB
- 4718adb86f6183b1cb69cfd7d1ee94ad2e9df9d5c4aa90de93a555b927a16815
- json477 B
- VERSION3 B
- layer.tar16 MB
- 699ca129c470aeab3a735bbd35b4211e9c963326efbd6fd8b23f65af6c3f9a81
- json477 B
- VERSION3 B
- layer.tar16 MB
- 634da23a7d009373413c71de477671daadba6de2c6722e12c4acb22576683861
- json477 B
- VERSION3 B
- layer.tar87 MB
- a370ece30b6abfa2a4ba91961a0ab0742b8079ca1b7a19ff9df46f07986f4ada
- json477 B
- VERSION3 B
- layer.tar6 MB
- de30e25bb840b06339cd2beef96ed51036ee17c314ab2bd3f2c17d0fd2151395
- json477 B
- VERSION3 B
- layer.tar3 kB
- cbe3962684ff9f23b7b335a553059effce146c73edd40b47c66c654cd287b20e
- json477 B
- VERSION3 B
- layer.tar142 MB
- d08d3825c03e0d6813de0d6a5a662f51ace7e3ac4f3850f0cdcc1a67eb0acc1b
- json1 kB
- VERSION3 B
- layer.tar56 MB
- e66f6399230051c42bf54f1c6375fbe8c35e8c2e5b9adb8ae474d4df3b44122e
- json477 B
- VERSION3 B
- layer.tar4 kB
- 86a5dd556cbc9126592da9ce7e8b252d4983eeb41438ee37c2f6c75845bc307c
- json477 B
- VERSION3 B
- layer.tar468 MB
- 63349ec265651864b5b4a10e1bdf9f9243ea87c5641c46dfbda45fdadc34f59e.json9 kB
- repositories99 B
- manifest.json1 kB
- Name
- moses-smt_is-en.tar.gz
- Size
- 5.3 GB
- Format
- application/gzip
- Description
- Trained IS-EN model
- MD5
- d2dcf5089d7d7cd68a3db46da5eff19c
- 88dc9157e2e1c4d9085bc8ed39b94c8f1d2072b74d22914d5097c24b6040df29
- json477 B
- VERSION3 B
- layer.tar968 kB
- aa0f56dfa64cbbe3a136d7409c95c6cb53b226ea551b0cd1b88033ef5e728cb8
- json477 B
- VERSION3 B
- layer.tar3 kB
- 0bd29a970da656512c70ecc4b6ab126177ac8bac18e0cae2ac49699956a0f2f4
- json477 B
- VERSION3 B
- layer.tar15 kB
- 90468fcf41a7dfb1562e614003e5473a8cb02cef0bfc8889653de47e3762c558
- json1 kB
- VERSION3 B
- layer.tar7 GB
- 4aa435637d457e59b44b4aa9a27c65bcf9619e11ed54b08b022f33a76682ba47
- json477 B
- VERSION3 B
- layer.tar721 MB
- b814aba80c68b70833d1881adc00d04764284169d1d2d9e6d5aebd2ab518aef3
- json401 B
- VERSION3 B
- layer.tar62 MB
- repositories99 B
- 7c7e0f36117a0c10439c2ea5d31c690d0fa2dc2edc5953592dc37a4fd16e2a0d.json6 kB
- manifest.json597 B
- Name
- moses-smt_en-is.tar.gz
- Size
- 5.17 GB
- Format
- application/gzip
- Description
- Trained EN-IS model
- MD5
- 12099d739edcc710afb7a879ef5a37fc
- 88dc9157e2e1c4d9085bc8ed39b94c8f1d2072b74d22914d5097c24b6040df29
- json477 B
- VERSION3 B
- layer.tar968 kB
- aa0f56dfa64cbbe3a136d7409c95c6cb53b226ea551b0cd1b88033ef5e728cb8
- json477 B
- VERSION3 B
- layer.tar3 kB
- fa8a0e6764e86f2513c409abad6322da169ea920676444b81cc3de9ba22ac6b9
- json1 kB
- VERSION3 B
- layer.tar7 GB
- 0bd29a970da656512c70ecc4b6ab126177ac8bac18e0cae2ac49699956a0f2f4
- json477 B
- VERSION3 B
- layer.tar15 kB
- 4aa435637d457e59b44b4aa9a27c65bcf9619e11ed54b08b022f33a76682ba47
- json477 B
- VERSION3 B
- layer.tar721 MB
- b814aba80c68b70833d1881adc00d04764284169d1d2d9e6d5aebd2ab518aef3
- json401 B
- VERSION3 B
- layer.tar62 MB
- repositories99 B
- 5bf80b65e90a19380510401dde2d8f530d335e2e5e180cd8a26db0a4babf6ae7.json6 kB
- manifest.json597 B