Part-of-speech tagging also called the grammatically tagging of a word is one of the most basic needs of Intelligent Text Processing. In this process, words are detected in terms of nouns, verbs, letters, and more details are provided in the form of tagging. This tool is one of the strongest Persian language taggers which is able to detect 14 key grammatical tags. These tags are respectively as follows:
Id | POS | معادل | Id | POS | معادل | Id | POS | معادل |
1 | AJ | صفت | 6 | N | اسم | 11 | PUNC | جداکننده |
2 | CL | شاخص | 7 | NUM | عدد | 12 | RES | متفرقه |
3 | CONJ | حرف ربط | 8 | P | حرف اضافه | 13 | V | فعل |
4 | DET | حرف تعریف | 9 | POSTP | حرف اضافه پسین (را) | 14 | ADV | قید |
5 | INT | حرف صوت | 10 | PRO | ضمیر |
Enriching and strengthening search engines, extracting machine keywords, recognizing names within texts and pronoun references are among many features of this system. Tests have shown that this tool is able to recognize part-of-speech tagging with about 98% accuracy with very high speed. It should be noted that its speed is around 100,000 words per second.