@inproceedings{vajrobol-2022-coli,
title = "{C}o{LI}-Kanglish: Word-Level Language Identification in Code-Mixed {K}annada-{E}nglish Texts Shared Task using the Distilka model",
author = "Vajrobol, Vajratiya",
editor = "Chakravarthi, Bharathi Raja and
Murugappan, Abirami and
Chinnappa, Dhivya and
Hane, Adeep and
Kumeresan, Prasanna Kumar and
Ponnusamy, Rahul",
booktitle = "Proceedings of the 19th International Conference on Natural Language Processing (ICON): Shared Task on Word Level Language Identification in Code-mixed Kannada-English Texts",
month = dec,
year = "2022",
address = "IIIT Delhi, New Delhi, India",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.icon-wlli.2",
pages = "7--11",
abstract = "Due to the intercultural demographic of online users, code-mixed language is often used by them to express themselves on social media. Language support to such users is based on the ability of a system to identify the constituent languages of the code-mixed language. Therefore, the process of language identification that helps in determining the language of individual textual entities from a code-mixed corpus is a current and relevant classification problem. Code-mixed texts are difficult to interpret and analyze from an algorithmic perspective. However, highly complex transformer- based techniques can be used to analyze and identify distinct languages of words in code-mixed texts. Kannada is one of the Dravidian languages which is spoken and written in Karnataka, India. This study aims to identify the language of individual words of texts from a corpus of code-mixed Kannada-English texts using transformer-based techniques. The proposed Distilka model was developed by fine-tuning the DistilBERT model using the code-mixed corpus. This model performed best on the official test dataset with a macro-averaged F1-score of 0.62 and weighted precision score of 0.86. The proposed solution ranked first in the shared task.",
}
Markdown (Informal)
[CoLI-Kanglish: Word-Level Language Identification in Code-Mixed Kannada-English Texts Shared Task using the Distilka model](https://aclanthology.org/2022.icon-wlli.2) (Vajrobol, ICON 2022)
ACL