Papers with code-mixing
Processing and Understanding Mixed Language Data (D19-2)
Copied to clipboard
| Challenge: | Multilingual communities exhibit code-mixing, mixing of two or more languages in a single conversation . social media and other informal interactive platforms are allowing code-switching in user-generated text . |
| Approach: | a tutorial aims to provide a foundation for researchers to study code-mixing in multilingual communities. |
| Outcome: | a tutorial aims to provide new researchers with a foundation in linguistics and computational aspects of code-mixing. |
Language Identification and Named Entity Recognition in Hinglish Code Mixed Tweets (P18-3)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is an important text analysis task . code-mixing occurs when lexical items and grammatical features from two languages appear in one sentence . |
| Approach: | They propose to use language identifiers, parts-of-speech tags and chunkers to analyze code-mixed data. |
| Outcome: | The proposed method outperforms the best baseline by 33.18%. |
ContrastiveMix: Overcoming Code-Mixing Dilemma in Cross-Lingual Transfer for Information Retrieval (2024.naacl-short)
Copied to clipboard
| Challenge: | Multilingual pretrained language models have been widely adopted in cross-lingual transfer . however, training mPLMs on code-mixed data is counterproductive . |
| Approach: | They propose a method that disentangles contrastive loss between conflicting objectives . they propose mPLMs that train on code-mixed data for information retrieval . |
| Outcome: | The proposed model outperforms mDPR in cross-lingual transfer tasks . it is effective in sentence-level and token-level zero-shot tasks despite lack of target language data . |
GCM: A Toolkit for Generating Synthetic Code-mixed Text (2021.eacl-demos)
Copied to clipboard
| Challenge: | Code-mixing is a spoken language phenomenon and is difficult to train in multilingual communities. |
| Approach: | They propose a tool that can automatically generate code-mixed data given parallel data in two languages. |
| Outcome: | The proposed tool can generate code-mixed data in two languages using two linguistic theories. |
SyMCoM - Syntactic Measure of Code Mixing A Study Of English-Hindi Code-Mixing (2022.findings-acl)
Copied to clipboard
| Challenge: | Recent work on code mixing in computational settings has leveraged social media code mixed texts to train NLP models. |
| Approach: | They propose to use language ID tags to measure syntactic variety in code-mixed text and their relationship with computational model performance. |
| Outcome: | The proposed measure can be applied to English(en)-hindi(hi) code-mixed datasets and compares them with other measures. |
Harmonizing Code-mixed Conversations: Personality-assisted Code-mixed Response Generation in Dialogues (2024.findings-eacl)
Copied to clipboard
| Challenge: | blending multiple languages within a single conversation presents a formidable challenge, given the wide-ranging variations influenced by individual speaking styles and cultural backgrounds. |
| Approach: | They propose a novel approach to harness the Big Five personality traits acquired in an unsupervised manner from code-mixed conversations to bolster the performance of response generation. |
| Outcome: | The proposed approach enhances contextual relevance and performance of the proposed model by combining personality traits with dialogue context. |
MUTANT: A Multi-sentential Code-mixed Hinglish Dataset (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods to identify code-mixed text are difficult to scale effectively and efficiently on multi-sentential data. |
| Approach: | They propose to identify multi-sentential code-mixed text (MCT) from multilingual articles using a token-level language-aware pipeline. |
| Outcome: | The proposed dataset includes 67k articles with 85k identified Hinglish MCTs. |
Bhaasha, Bhāṣā, Zaban: A Survey for Low-Resourced Languages in South Asia – Current Stage and Challenges (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a survey examines the current efforts and challenges of NLP models for South Asian languages . there are more than 650 languages in South Asia, but many have very limited computational resources or are missing from existing models. |
| Approach: | a survey examines efforts and challenges of NLP for South Asian languages . they focus on transformer-based models such as BERT, T5, & GPT . findings highlight substantial issues, including missing data in critical domains . |
| Outcome: | The findings highlight significant issues, including missing data in critical domains . the survey aims to raise awareness within the NLP community for more targeted data curation . |
Towards Automating Healthcare Question Answering in a Noisy Multilingual Low-Resource Setting (P19-1)
Copied to clipboard
| Challenge: | a study aims to automate a multilingual digital helpdesk service available via text messaging to pregnant and breastfeeding mothers in South Africa. |
| Approach: | They examine a multilingual digital helpdesk service available via text messaging to pregnant and breastfeeding mothers in South Africa. |
| Outcome: | The proposed model can accelerate response time by several orders of magnitude. |
Predicting Foreign Language Usage from English-Only Social Media Posts (N18-2)
Copied to clipboard
| Challenge: | Social media is known for its multi-cultural and multilingual interactions, a natural product of which is code-mixing. |
| Approach: | They analyze 6 million tweets produced by 27 thousand multilingual users speaking 12 other languages besides English to build predictive models to infer non-English languages users speak exclusively from their tweets. |
| Outcome: | The proposed models are based on a corpus of 6 million tweets produced by 27 thousand multilingual users speaking 12 other languages besides English . they show that content, style and syntax are the most predictive of non-English languages that users speak on Twitter. |
Language Patterns and Behaviour of the Peer Supporters in Multilingual Healthcare Conversational Forums (2022.lrec-1)
Copied to clipboard
Ishani Mondal, Kalika Bali, Mohit Jain, Monojit Choudhury, Jacki O’Neill, Millicent Ochieng, Kagnoya Awori, Keshet Ronen
| Challenge: | a quantitative linguistic analysis of multilingual peer supporters in health-focused WhatsApp forums in Kenya is needed. |
| Approach: | They conduct a quantitative linguistic analysis of the language usage patterns of multilingual peer supporters in two health-focused WhatsApp forums in Kenya. |
| Outcome: | The proposed language analyzer can be used to analyze language usage patterns in two health-focused WhatsApp forums in Kenya. |
CodeMixBench: Evaluating Code-Mixing Capabilities of LLMs Across 18 Languages (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing benchmarks for large language models (LLMs) are limited by their narrow language pairs and tasks, failing to adequately assess their code-mixing abilities. |
| Approach: | They propose a benchmark to assess large language models' (LLMs) code-mixing abilities that covers eight tasks and 18 languages from seven language families. |
| Outcome: | The proposed method combines word substitution with GPT-4 prompting to generate large-scale synthetic code-mixed texts. |
MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NER (2022.acl-long)
Copied to clipboard
| Challenge: | Named entity recognition (NER) tasks have limited amount of labeled data . data augmentation methods suffer from token-label misalignment, which leads to unsatsifactory performance. |
| Approach: | They propose a data augmentation framework that explicitly injects NER labels into sentence context and generates high-quality augmented data with novel entities. |
| Outcome: | The proposed framework outperforms baseline methods on low-resource tasks. |
Identifying Tension in Holocaust Survivors’ Interview: Code-switching/Code-mixing as Cues (2022.lrec-1)
Copied to clipboard
| Challenge: | Using CS/CM as a linguistic phenomenon could be a sign of tension in Holocaust survivors’ interviews. |
| Approach: | They annotated CS/CM codes and annotate silence situations in an open corpus . they found that most annotations were captured in the tension places . |
| Outcome: | The proposed method shows that annotations are captured in the tension places . the study calls for more research endeavors on tension detection . |
Humor Detection in English-Hindi Code-Mixed Social Media Content : Corpus and Baseline System (L18-1)
Copied to clipboard
| Challenge: | a growing number of social media users are using code-mixing to detect humor . linguistics researchers are looking for methods to detect humorous content in text . |
| Approach: | They analyze a corpus of English-Hindi code-mixed tweets annotated with humorous(H) tags. |
| Outcome: | The proposed method detects humor in code-mixed tweets in English-Hindi. |
COMMIT: Code-Mixing English-Centric Large Language Model for Multilingual Instruction Tuning (2024.findings-naacl)
Copied to clipboard
| Challenge: | COMMIT improves the exact match score of low-resource language QA by 32x. |
| Approach: | They propose to specialize instruction tuning to deviate from English-centric instruction tuning . they propose to perform cross-lingual alignment to overcome data imbalance . |
| Outcome: | The proposed method improves the exact match score of low-resource language QA by 32x. |
A Semi-supervised Approach to Generate the Code-Mixed Text using Pre-trained Encoder and Transfer Learning (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to train neural network-based models for code-mixing are limited due to language specificity of code-mixed text. |
| Approach: | They propose a deep learning approach to generate code-mixed text from English to multiple languages without any parallel data. |
| Outcome: | The proposed approach generates a code-mixed text from English to multiple languages without any parallel data. |
BRCC and SentiBahasaRojak: The First Bahasa Rojak Corpus for Pretraining and Sentiment Analysis Dataset (2022.coling-1)
Copied to clipboard
| Challenge: | Code-mixing is prevalent in multilingual societies and is challenging to train . we use data augmentation to build a model to deal with code-mixed inputs . |
| Approach: | They propose to train a model to deal with code-mixing phenomena of Bahasa Rojak using data augmentation to construct a Bahasan Rojakin corpus and a pre-trained model to process input tokens. |
| Outcome: | The proposed model can tag the language of the input token automatically to process code-mixing input. |
Exploring Methods for Building Dialects-Mandarin Code-Mixing Corpora: A Case Study in Taiwanese Hokkien (2022.findings-emnlp)
Copied to clipboard
| Challenge: | CM is a challenging task when mixed languages include dialects. |
| Approach: | They propose to construct a Hokkien-Mandarin CM dataset to overcome the limitation . they propose to use a linguistics-based toolkit to train the model for translation tasks . |
| Outcome: | The proposed model achieves good results on CM data translation while maintaining monolingual translation quality. |
HateCheckHIn: Evaluating Hindi Hate Speech Detection Models (2022.lrec-1)
Copied to clipboard
| Challenge: | Hate speech detection models are evaluated on a held-out test data, but they are incapable of identifying weaknesses. |
| Approach: | They propose to use multilingual hate speech detection models to evaluate their performance on social media conversation. |
| Outcome: | The proposed model can detect hate speech in multiple languages using a real-world conversation on social media. |
Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) exhibit impressive zero/few-shot inference and generation quality for high-resource languages (HRLs). |
| Approach: | They propose to reduce the cost of processing LRLs by code-mixing, translation, and transliteration of LRL to HRLs to ensure that predictive and generative qualities are not compromised. |
| Outcome: | The proposed model reduces the cost of processing LRLs while ensuring that predictive and generative qualities are not compromised. |
MaCmS: Magahi Code-mixed Dataset for Sentiment Analysis (2024.lrec-main)
Copied to clipboard
| Challenge: | Sociolinguists and psychologists have been studying these variations in the lexicons and the language from the 50's . code-mixing is a popular method for understanding people's emotions and attitudes towards various subjects, but low-resourced languages often have a mix of scripts and languages. |
| Approach: | They introduce a new sentiment data, MaCMS, for Magahi-Hindi-English code-mixed language, where Magai is a less-resourced minority language. |
| Outcome: | The proposed dataset is the first Magahi-Hindi-English code-mixed dataset for sentiment analysis tasks. |
Word-Level Detection of Code-Mixed Hate Speech with Multilingual Domain Transfer (2025.findings-acl)
Copied to clipboard
| Challenge: | a growing problem in language detection tasks is code-mixing, a combination of more than one language . lack of available datasets for code-mixing causes the problem . authors propose a multilingual approach to code-matching . |
| Approach: | They propose to use an annotated hate speech dataset to detect code-mixing in profane language . they propose to apply bilingual fine-tuned models to code-mixed hate speech in german rap lyrics . |
| Outcome: | The proposed model can detect code-mixed hate speech and neologisms in German rap lyrics . the proposed model is more nuanced than binary classification . |