This is a simple script that split an Amharic document into different sentences and tokenes. If you find an issue, please let us know in the GitHub Issues
The Segmenter is part of the Semantic Models for Amharic Project
- Install the segmenter:
pip install amseg
from amseg.amharicSegmenter import AmharicSegmenter
sent_punct = []
word_punct = []
segmenter = AmharicSegmenter(sent_punct,word_punct)
words = segmenter.amharic_tokenizer("እአበበ በሶ በላ።")
sentences = segmenter.tokenize_sentence("እአበበ በሶ በላ። ከበደ ጆንያ፤ ተሸከመ፡!ለምን?")
Outputs
words = ['እአበበ', 'በሶ', 'በላ', '።']
sentences = ['እአበበ በሶ በላ።', 'ከበደ ጆንያ፤ ተሸከመ፡!', 'ለምን?']
from amseg.amharicNormalizer import AmharicNormalizer as normalizer
from amseg.amharicRomanizer import AmharicRomanizer as romanizer
normalized = normalizer.normalize('ሑለት ሦስት')
romanized = romanizer.romanize('ሑለት ሦስት')
Outputs
normalized = 'ሁለት ሶስት'
romanized = 'ḥulat śosət'
🎉 🎉 The Amharic Segmenter is released and can be installed as pip install amseg 🎉 :tada
To cite the Amharic segmenter/tokenizer tool, use the following paper
@Article{fi13110275,
AUTHOR = {Yimam, Seid Muhie and Ayele, Abinew Ali and Venkatesh, Gopalakrishnan and Gashaw, Ibrahim and Biemann, Chris},
TITLE = {Introducing Various Semantic Models for Amharic: Experimentation and Evaluation with Multiple Tasks and Datasets},
JOURNAL = {Future Internet},
VOLUME = {13},
YEAR = {2021},
NUMBER = {11},
ARTICLE-NUMBER = {275},
URL = {https://www.mdpi.com/1999-5903/13/11/275},
ISSN = {1999-5903},
DOI = {10.3390/fi13110275}
}