code-mixed

A curated list of research papers and resources on code-switching

CodeSwitch is a NLP tool, can use for language identification, pos tagging, name entity recognition, sentiment analysis of code mixed data.

The main aim of the project is to develop a sentiment analyzer that can be used on twitter data to classify it as positive or negative. Our project takes care of the challenge of bilingual comments, where people tweet in two languages, in this case Hindi and English, in the Latin Alphabet.

CalBERT - Code-mixed Adaptive Language representations using BERT, published at AAAI-MAKE 2022

Unsupervised Sentiment Analysis for Code-mixed Data

Implementation for the paper titled, " Data-Augmentation for Bangla-English Code-Mixed Sentiment Analysis: Enhancing Cross Linguistic Contextual Understanding", IEEE Access, 2023

This repository contains the system description and the codes that we implemented for participating in EACL-2021 shared tasks.

This project focuses on fine-tuning Llama 3.2 (1B) to generate structured YAML automation commands in Nepali-English, optimized for low-resource deployment.

Multilingual scam detection for Indian SMS and WhatsApp messages, including code-mixed and romanised text, with tactic-level explanations. Fine-tuned XLM-R (int8 ONNX) vs a TF-IDF baseline, adversarial robustness testing, FastAPI service with observability.

A code-mixed annotation tool aimed at increasing the annotation quality whilst reducing the annotation time and various overheads associated with code-mixed data.

Reproducible IR benchmark for Hinglish / code-mixed product search on Amazon ESCI: BM25 vs multilingual dense vs LLM reranking, evaluated with nDCG/MRR + failure analysis.

This repository implements a Hidden Markov Model (HMM) for performing Parts of Speech (POS) Tagging on Assamese-English code-mixed texts.

This repository implements a Long Short Term Memory (LSTM) for performing Parts-of-Speech (POS) Tagging on Assamese-English code-mixed texts.

The code for SOP project done for the topic of Abuse detection in multilingual code-switched and code-mixed language using federated learning

This repository implements a Conditional Random Field (CRF) for performing Parts-of-Speech (POS) Tagging on Assamese-English code-mixed texts.

302-Person-Hindi-and-English-Bilingual-Spontaneous-Monologue-smartphone-speech-dataset

This repository implements a Bidirectional Long Short Term Memory (BiLSTM) for performing Parts-of-Speech (POS) Tagging on Assamese-English code-mixed texts.

An advanced AI system for detecting toxic, offensive, and abusive content in code-mixed languages (Hinglish) with Context-Awareness, Emotion Tracking, and Explainable AI (XAI).