Colloquial Persian POS (CPPOS) Corpus: A Novel Corpus for Colloquial Persian Part of Speech Tagging

TL;DR

This paper introduces CPPOS, a new annotated corpus of colloquial Persian from social media, enabling improved POS tagging with deep learning models, outperforming previous resources by 14%.

Contribution

The creation of the first large-scale colloquial Persian POS corpus with manual annotation and a new tagging guideline, tailored for social media text.

Findings

Deep learning models trained on CPPOS outperform previous models.

The corpus achieves a 14% improvement in POS tagging accuracy.

Manual annotation ensures high-quality, domain-specific data.

Abstract

Introduction: Part-of-Speech (POS) Tagging, the process of classifying words into their respective parts of speech (e.g., verb or noun), is essential in various natural language processing applications. POS tagging is a crucial preprocessing task for applications like machine translation, question answering, sentiment analysis, etc. However, existing corpora for POS tagging in Persian mainly consist of formal texts, such as daily news and newspapers. As a result, smart POS tools, machine learning models, and deep learning models trained on these corpora may not perform optimally for processing colloquial text in social network analysis. Method: This paper introduces a novel corpus, "Colloquial Persian POS" (CPPOS), specifically designed to support colloquial Persian text. The corpus includes formal and informal text collected from various domains such as political, social, and commercial on Telegram, Twitter, and Instagram more than 520K labeled tokens. After collecting posts from these social platforms for one year, special preprocessing steps were conducted, including normalization, sentence tokenizing, and word tokenizing for social text. The tokens and sentences were then manually annotated and verified by a team of linguistic experts. This study also defines a POS tagging guideline for annotating the data and conducting the annotation process. Results: To evaluate the quality of CPPOS, various deep learning models, such as the RNN family, were trained using the constructed corpus. A comparison with another well-known Persian POS corpus named "Bijankhan" and the Persian Hazm POS tool trained on Bijankhan revealed that our model trained on CPPOS outperforms them. With the new corpus and the BiLSTM deep neural model, we achieved a 14% improvement over the previous dataset.