In this system paper for SemEval-2024 Task 1 subtask A, we present our approach to evaluating the semantic relatedness of sentence pairs in nine languages. We use a mix of statistical methods combined with fine-tuned BERT transformer models for English and use the same model and machine-translated data for the other languages. This simplistic approach shows consistently reliable scores and achieves above-average rank in all languages.

In this system paper for SemEval-2024 Task3 subtask 2, I present my simple textual approach to emotion classification and emotion cause analysis in conversations using machine learning and next sentence prediction. I train a SpaCy model for emotion classification and use next sentence prediction with BERT for emotion cause analysis. While speaker names and audio-visual clips are given in addition to text of the conversations, my approach uses textual data only to test my methodology to combine machine learning with next sentence prediction. This paper reveals both strengths and weaknesses of my trial, suggesting a direction of future studies to improve my introductory solution.

In this system paper for SemEval-2024 Task4 subtask 2b, I present my approach to identifying propagandistic memes in multiple languages. I firstly establish a baseline for English and then implement the model into other languages (Bulgarian, North Macedonian and Arabic) by using machine translation. Data from other subtasks (subtask 1, subtask 2a) are also used in addition to data for this subtask, and additional data from Kaggle are concatenated to these in order to enhance the model. The results show a high reliability of my English baseline and a room for improvement of its implementation.

In this system paper for SemEval-2024 Task10 subtask 1 (ERC), I present my approach to recognizing emotions in Hindi-English codemixed conversations. I train a SpaCy model with English translated data and classify emotions behind Hindi-English code-mixed utterances by using the model and translating them into English. I use machine translation to translate all the data in Hindi-English mixed language into English due to an easy access to existing data for emotion recognition in English. Some additional data in English are used to enhance my model. This English based approach demonstrates a fundamental possibility and potential of simplifying code-mixed language into one major language for emotion recognition.