import requests
# Get result in XML format
url = "http://oujda-nlp-team.net:8082/api/pos"
text_input = "##############################"
data = {"textinput": text_input}
response = requests.post(url, data=data)
if response.status_code == 200:
result = response.text
print(f"Result in text format: {result}")
else:
print("Error during API request.")
This POS tagger was developed for Arabic texts taking into account the agglutination structure very present in the Arabic language. It uses a very rich tagset containing compound tags that provide syntactic information on the clitics attached to words. This system uses a probabilistic model and the Alkhalil_Morpho_Sys analyzer to identify the correct tags in the context. To build the model, we used 90% of the Nemlar labeled corpus, consisting of approximately 500,000 words, during the training phase, and the remaining 10% was devoted to the testing phase. The precision obtained is around 94%.
For further details, please check the following paper :
- Ababou, N.; Mazroui. A.; “A hybrid Arabic POS tagging for simple and compound morphosyntactic tags”. International Journal of Speech Technology 2016, vol. 19, no 2, p. 289-302.

