Large language models (LLMs) have gained popularity recently due to their outstanding performance in various downstream Natural Language Processing (NLP) tasks. However, low-resource languages are still lagging behind current state-of-the-art (SOTA) developments in the field of NLP due to insufficient resources to train LLMs. Ethiopian languages exhibit remarkable linguistic diversity, encompassing a wide array of scripts, and are imbued with profound religious and cultural significance. This paper introduces EthioLLM – multilingual large language models for five Ethiopian languages (Amharic, Ge’ez, Afan Oromo, Somali, and Tigrinya) and English, and Ethiobenchmark – a new benchmark dataset for various downstream NLP tasks. We evaluate the performance of these models across five downstream NLP tasks. We open-source our multilingual language models, new benchmark datasets for various downstream tasks, and task-specific fine-tuned language models and discuss the performance of the models. Our dataset and models are available at the https://huggingface.co/EthioNLP repository.

This research paper focuses on sentiment analysis of Tamil and Tulu texts using a BERT model and an RNN model. The BERT model, which was pretrained, achieved satisfactory performance for the Tulu language, with a Macro F1 score of 0.352. On the other hand, the RNN model showed good performance for Tamil language sentiment analysis, obtaining a Macro F1 score of 0.208. As future work, the researchers aim to fine-tune the models to further improve their results after the training process.

This research focuses on identifying abusive language in comments. The study utilizes deep learning models, including Long Short-Term Memory (LSTM) and Recurrent Neural Networks (RNNs), to analyze linguistic patterns. Specifically, the LSTM model, a type of RNN, is used to understand the context by capturing long-term dependencies and intricate patterns in the input sequences. The LSTM model achieves better accuracy and is enhanced through the addition of a dropout layer and early stopping. For detecting abusive language in Telugu and Tamil-English, an LSTM model is employed, while in Tamil abusive language detection, a word-level RNN is developed to identify abusive words. These models process text sequentially, considering overall content and capturing contextual dependencies.

Language Identification at the Word Level in Kannada-English Texts. This paper describes the system paper of CoLI-Kanglish 2022 shared task. The goal of this task is to identify the different languages used in CoLI-Kanglish 2022. This dataset is distributed into different categories including Kannada, English, Mixed-Language, Location, Name, and Others. This Code-Mix was compiled by CoLI-Kanglish 2022 organizers from posts on social media. We use two classification techniques, KNN and SVM, and achieve an F1-score of 0.58 and place third out of nine competitors.

The goal of code-mixed language identification (LID) is to determine which language is spoken or written in a given segment of a speech, word, sentence, or document. Our task is to identify English, Kannada, and mixed language from the provided data. To train a model we used the CoLI-Kenglish dataset, which contains English, Kannada, and mixed-language words. In our work, we conducted several experiments in order to obtain the best performing model. Then, we implemented the best model by using Bidirectional Long Short Term Memory (Bi-LSTM), which outperformed the other trained models with an F1-score of 0.61%.