In this paper, we present CMCLIP, a Code-Mixed Contrastive Linked Image Pre-trained model, an innovative extension of the widely recognized CLIP model. Our work adapts the CLIP framework to the code-mixed environment through a novel cross-lingual teacher training methodology. Building on the strengths of CLIP, we introduce the first code-mixed pre-trained text-and-vision model, CMCLIP, specifically designed for Hindi-English code-mixed multimodal language settings. The model is developed in two variants: CMCLIP-RB, based on ResNet, and CMCLIP-VX, based on ViT, both of which adapt the original CLIP model to suit code-mixed data. We also introduce a large, novel dataset called Parallel Hybrid Multimodal Code-mixed Hinglish (PHMCH), which forms the foundation for teacher training. The CMCLIP models are evaluated on various downstream tasks, including code-mixed Image-Text Retrieval (ITR) and classification tasks, such as humor and sarcasm detection, using a code-mixed meme dataset. Our experimental results demonstrate that CMCLIP outperforms existing models, such as M3P and multilingual-CLIP, establishing state-of-the-art performance for code-mixed multimodal tasks. We would also like to assert that although our data and frameworks are on Hindi-English code-mix, they can be extended to any other code-mixed language settings.

Codemixing, the linguistic phenomenon where a speaker alternates between two or more languages within a conversation or even a single utterance, presents a significant challenge for machine translation systems due to its syntactic complexity and contextual nuances. This paper introduces a set of advanced transformerbased models fine-tuned specifically for translating codemixed text to English, more specifically, Hindi-English (colloquially referred to as Hinglish) codemixed text into English. Unlike standard bilingual corpora, codemixed data requires an understanding of the intricacies of grammatical structures and cultural contexts embedded within the language blend. Existing machine translation efforts in codemixed languages have largely been constrained by the paucity of robust datasets and models that can capture the nuanced semantic and syntactic interplay characteristic of such languages. We present a novel dataset PACMAN trans for Hinglish to English machine translation, based on the PACMAN strategy, meticulously curated to represent natural codemixing patterns. Our generic fine-tuned translation models trained on the novel data outperforms current state-of-theart Large Language Models (LLMs) by 38% in terms of BLEU score. Further, when fine-tuned on custom benchmark datasets, our focused dual fine-tuned models surpass the PHINC dataset BLEU score benchmark by 22%. Our comparative analysis illustrates significant improvements in translation quality, showcasing the potential of fine-tuning transformer models in bridging the linguistic divide in codemixed language translation. The success of our models reflects a promising step forward in the quest to provide seamless translation services for the ever-growing multilingual population and the complex linguistic phenomena they generate.

Code-mixing or Code-switching is the mixing of languages in the same context, predominantly observed in multilingual societies. The existing code-mixed datasets are small and primarily contain social media text that does not adhere to standard spelling and grammar. Computational models built on such data fail to generalise on unseen code-mixed data. To address the unavailability of quality code-mixed annotated datasets, we explore the combined task of generating annotated code mixed data, and building computational models from this generated data, specifically for code-mixed Part-Of-Speech (POS) tagging. We introduce PACMAN(PArallel CodeMixed dAta generatioN) - a synthetically generated code-mixed POS tagged dataset, with above 50K samples, which is the largest annotated code-mixed dataset. We build POS taggers using classical machine learning and deep learning based techniques on the generated data to report an F1-score of 98% (8% above current State-of-the-art (SOTA)). To determine the efficacy of our data, we compare it against the existing benchmark in code-mixed POS tagging. PACMAN outperforms the benchmark, ratifying that our dataset and, subsequently, our POS tagging models are generalised and capable of handling even natural code-mixed and monolingual data.

Deep learning based methods have shown tremendous success in several Natural Language Processing (NLP) tasks. The recent trends in the usage of Deep Learning based models for natural language tasks have definitely produced incredible performance for several application areas. However, one major problem that most of these models face is the lack of transparency, i.e. the actual decision process of the underlying model is not explainable. In this paper, at first we solve a very fundamental problem of Natural Language Understanding (NLU), i.e. intent detection using a Bi-directional Long Short Term Memory (BiLSTM). In order to determine the defining features that lead to a specific intent class, we use the Layerwise Relevance Propagation (LRP) algorithm to find the defining feature(s). In the process, we conclude that saliency method of eLRP (epsilon Layerwise Relevance Propagation) is a prominent process for highlighting the important features of the input responsible for the current classification which results in significant insights to the inner workings, such as the reasons for misclassification by the black box model.