ABLTagger (PoS) - 1.0.0

Clarin IS Repository

Authors: Jónsson, Haukur Páll ; Loftsson, Hrafn and Steingrímsson, Steinþór

Item identifier: http://hdl.handle.net/20.500.12537/53

Project URL: https://github.com/cadia-lvl/POS

Date issued: 2020-09-14

Type: toolService

Language(s): Icelandic

Description: A Part-of-Speech (PoS) tagger for Icelandic. In this submission, you will find ABLTagger v1.0.0. This is a PoS tagger that works with the revised tagset and achieves an accuracy of 95.59% on MIM-Gold (cross-validation). For additional details, error analysis and categorization of this tagger and other taggers (including a previous version of ABLTagger), see I4 report for milestone (2020) in Language Technology Programme for Icelandic 2019-2023. For the most recent versions, installation, usage, and other instructions see https://github.com/cadia-lvl/POS on CLARIN: - Python wheel, version 1.0.0 - GitHub repository at version 1.0.0 - Model files (tagger and dictionaries) - Docker image, version 1.0.0 ------------------------------------------------------------------------------------------- Markari fyrir íslensku. Í þessum pakka er ABLTagger v.1.0.0. Þetta er markari sem virkar fyrir nýja markamengið og nær 95.59% nákvæmni á MÍM-Gull (krossprófanir). Fyrir nánari upplýsingar, villugreiningu og villuflokkun fyrir þennan markara og aðra (ásamt fyrri útgáfu af þessum markara), sjá I4 skýrslu fyrir vörðu 3 (2020) í Máltækniáætlun fyrir íslensku 2019-2023. Fyrir nýjustu útgáfur, uppsetninga-, notenda- og aðrar leiðbeiningar sjá https://github.com/cadia-lvl/POS Á CLARIN: - Python wheel, útgáfa 1.0.0 - GitHub repository af útgáfu 1.0.0 - Líkan (markari and orðabækur) - Docker mynd, útgáfa 1.0.0

Publisher: Reykjavik University

Subject(s): pos-tagging morphosyntactic tagging

Collection(s): Clarin IS

This item is replaced by a newer submission:

http://hdl.handle.net/20.500.12537/115

Show full item record

Files in this item

Download all files in item (8.58 GB)

This item is

Publicly Available

and licensed under:
Apache License 2.0

Name: pos-1.0.0-py3-none-any.whl
Size: 31.13 KB
Format: Unknown
Description: Python wheel
MD5: 553881982f386fa7d512c13b4b9fb19c

Name: dictionaries.pickle
Size: 159.46 MB
Format: Unknown
Description: Dictionaries for model
MD5: e618d06f69491e7acbc0e794e75b30cb

Name: tagger.pt
Size: 2.24 GB
Format: Unknown
Description: The model
MD5: 7b27facdb1167fbf28a3fce911d94671

Name: pos-1.0.0.tar
Size: 6.17 GB
Format: Unknown
Description: Docker image
MD5: 2138f1d752c1f237ad8f46bfa71a1b28

Name: POS-1.0.0.tar.gz
Size: 728.87 KB
Format: application/gzip
Description: GitHub repo
MD5: eda09ba229d0d4b45d2ffaf9db6c06a5

Download file Preview

File Preview

POS-1.0.0
- src
  - pos
    - __init__.py97 B
    - model.py14 kB
    - types.py6 kB
    - evaluate.py6 kB
    - flair_embeddings.py2 kB
    - data.py9 kB
    - cli.py15 kB
    - api.py4 kB
    - vectorize_dim.py21 kB
    - train.py9 kB
- poetry.lock142 kB
- README.md9 kB
- .gitignore130 B
- tests
  - test_untagged.tsv32 B
  - test_tensor.py2 kB
  - test.tsv44 B
  - test_pred.tsv56 B
  - test_data.py18 kB
  - test_flair.py287 B
- data
  - extra
    - all_tags.txt3 kB
    - characters_training.txt335 B
- pyproject.toml1 kB
- Dockerfile399 B
- example.py561 B
- .github
  - workflows
    - python-package.yml1 kB
- LICENSE11 kB
- example.txt37 B
- bin
  - gold-9-fold.sh1 kB
  - full_model.sh873 B
  - mim_otb-10-fold.sh1 kB
  - ifd-9-fold.sh1012 B
  - evaluate_rmh_subcorpora.sh223 B
  - ifd+gold-9-fold.sh1 kB
  - run_experiment.sh1 kB
  - analyse_results.ipynb1 MB
- pax_global_header52 B

Partners, Coordination, Funding

Repository

More

CLARIN-IS is fully supported by the Ministry of Culture and Business Affairs

Copyright (c) 2023. Arni Magnusson Institute for Icelandic Studies. All rights reserved.