Part of Speech Tagging: Shallow or Deep Learning?
Deep neural networks have advanced the state of the art in numerous fields, but they generally suffer from low computational efficiency and the level of improvement compared to more efficient machine learning models is not always significant. We perform a thorough PoS tagging evaluation on the Univ...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Linköping University Electronic Press
2018-06-01
|
| Series: | Northern European Journal of Language Technology |
| Subjects: | |
| Online Access: | https://nejlt.ep.liu.se/article/view/218 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590588455682048 |
|---|---|
| author | Robert Östling |
| author_facet | Robert Östling |
| author_sort | Robert Östling |
| collection | DOAJ |
| description |
Deep neural networks have advanced the state of the art in numerous fields, but they generally suffer from low computational efficiency and the level of improvement compared to more efficient machine learning models is not always significant. We perform a thorough PoS tagging evaluation on the Universal Dependencies treebanks, pitting a state-of-the-art neural network approach against UDPipe and our sparse structured perceptron-based tagger, efselab. In terms of computational efficiency, efselab is three orders of magnitude faster than the neural network model, while being more accurate than either of the other systems on 47 of 65 treebanks.
|
| format | Article |
| id | doaj-art-26ca654a234e4895969680278cc3bfbc |
| institution | Kabale University |
| issn | 2000-1533 |
| language | English |
| publishDate | 2018-06-01 |
| publisher | Linköping University Electronic Press |
| record_format | Article |
| series | Northern European Journal of Language Technology |
| spelling | doaj-art-26ca654a234e4895969680278cc3bfbc2025-01-23T10:36:32ZengLinköping University Electronic PressNorthern European Journal of Language Technology2000-15332018-06-01510.3384/nejlt.2000-1533.1851Part of Speech Tagging: Shallow or Deep Learning?Robert Östling0Stockholm University, Department of Linguistics Deep neural networks have advanced the state of the art in numerous fields, but they generally suffer from low computational efficiency and the level of improvement compared to more efficient machine learning models is not always significant. We perform a thorough PoS tagging evaluation on the Universal Dependencies treebanks, pitting a state-of-the-art neural network approach against UDPipe and our sparse structured perceptron-based tagger, efselab. In terms of computational efficiency, efselab is three orders of magnitude faster than the neural network model, while being more accurate than either of the other systems on 47 of 65 treebanks. https://nejlt.ep.liu.se/article/view/218pos taggingsequence labelingstructured perceptrondeep learningneural networksuniversal dependencies |
| spellingShingle | Robert Östling Part of Speech Tagging: Shallow or Deep Learning? Northern European Journal of Language Technology pos tagging sequence labeling structured perceptron deep learning neural networks universal dependencies |
| title | Part of Speech Tagging: Shallow or Deep Learning? |
| title_full | Part of Speech Tagging: Shallow or Deep Learning? |
| title_fullStr | Part of Speech Tagging: Shallow or Deep Learning? |
| title_full_unstemmed | Part of Speech Tagging: Shallow or Deep Learning? |
| title_short | Part of Speech Tagging: Shallow or Deep Learning? |
| title_sort | part of speech tagging shallow or deep learning |
| topic | pos tagging sequence labeling structured perceptron deep learning neural networks universal dependencies |
| url | https://nejlt.ep.liu.se/article/view/218 |
| work_keys_str_mv | AT robertostling partofspeechtaggingshallowordeeplearning |