mlsanityData to 14 Oct 2026

HinGE: A Dataset for Generation and Evaluation of Code-Mixed Hinglish Text

arXiv 2107.03760 ↗First posted 8 Jul 2021cs.CLcited by 28

Not on the map. Why?

Abstract (arXiv)

Text generation is a highly active area of research in the computational linguistic community. The evaluation of the generated text is a challenging task and multiple theories and metrics have been proposed over the years. Unfortunately, text generation and evaluation are relatively understudied due to the scarcity of high-quality resources in code-mixed languages where the words and phrases from multiple languages are mixed in a single utterance of text and speech. To address this challenge, we present a corpus (HinGE) for a widely popular code-mixed language Hinglish (code-mixing of Hindi and English languages). HinGE has Hinglish sentences generated by humans as well as two rule-based algorithms corresponding to the parallel Hindi-English sentences. In addition, we demonstrate the inefficacy of widely-used evaluation metrics on the code-mixed data. The HinGE dataset will facilitate the progress of natural language generation research in code-mixed languages.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 15 of its 37 references that are in the map. First posted on arXiv 8 Jul 2021.

Builds on

15 of 37 references.

References · 15

  1. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  2. 2016Enriching Word Vectors with Subword Informationcited by 1,583
  3. 2018A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddingscited by 146
  4. 2017The IIT Bombay English-Hindi Parallel Corpuscited by 75
  5. 2020SemEval-2020 Task 9: Overview of Sentiment Analysis of Code-Mixed Tweetscited by 62
  6. 2019Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentencescited by 55
  7. 2020PHINC: A Parallel Hinglish Social Media Code-Mixed Corpus for Machine Translationcited by 38
  8. 2016Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Textcited by 31
  9. 2021Challenges and Limitations with the Metrics Measuring the Complexity of Code-Mixed Textcited by 18
  10. 2018A Dataset for Building Code-Mixed Goal Oriented Conversation Systemscited by 16
  11. 2018A Corpus of English-Hindi Code-Mixed Tweets for Sarcasm Detectioncited by 15
  12. 2019Cross-Lingual Dependency Parsing Using Code-Mixed TreeBankcited by 10
3 more
  1. 2018Learn to Code-Switch: Data Augmentation using Copy Mechanism on Language Modelingcited by 9
  2. 2017All that is English may be Hindi: Enhancing language identification through automatic ranking of likeliness of word borrowing in social mediacited by 7
  3. 2020Codeswitched Sentence Creation using Dependency Parsingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 12; 2023: 4; 2024: 6; 2025: 3; 2026: 1.

28 papers.

Sort:

By area:

  1. 2022The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challengescited by 35
  2. 2022L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Modelscited by 34
  3. 2022ArzEn-ST: A Three-way Speech Translation Corpus for Code-Switched Egyptian Arabic - Englishcited by 13
  4. 2021MIPE: A Metric Independent Pipeline for Effective Code-Mixed NLG Evaluationcited by 7
  5. 2021Quality Evaluation of the Low-Resource Synthetically Generated Code-Mixed Hinglish Textcited by 7
  6. 2024Code-Mixer Ya Nahi: Novel Approaches to Measuring Multilingual LLMs' Code-Mixing Capabilitiescited by 7
  7. 2025COMI-LINGUA: Expert Annotated Large-Scale Dataset for Multitask NLP in Hindi-English Code-Mixingcited by 7
  8. 2024Linguistics Theory Meets LLM: Code-Switched Text Generation via Equivalence Constrained Large Language Modelscited by 6
  9. 2024CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedbackcited by 5
  10. 2022Language Agnostic Code-Mixing Data Augmentation by Predicting Linguistic Patternscited by 3
  11. 2023Persona-aware Generative Model for Code-mixed Languagecited by 3
  12. 2024Multilingual Controlled Generation And Gold-Standard-Agnostic Evaluation of Code-Mixed Sentencescited by 3
16 more
  1. 2025DIVERS-Bench: Evaluating Language Identification Across Domain Shifts and Code-Switchingcited by 3
  2. 2023MUTANT: A Multi-sentential Code-mixed Hinglish Datasetcited by 2
  3. 2023My Boli: Code-mixed Marathi-English Corpora, Pretrained Language Models and Evaluation Benchmarkscited by 2
  4. 2023Marathi-English Code-mixed Text Generationcited by 2
  5. 2024Grammatical Error Correction for Code-Switched Sentences by Learners of Englishcited by 2
  6. 2022niksss at HinglishEval: Language-agnostic BERT-based Contextual Embeddings with Catboost for Quality Evaluation of the Low-Resource Synthetically Generated Code-Mixed Hinglish Textcited by 1
  7. 2022SIT at MixMT 2022: Fluent Translation Built on Giant Pre-trained Modelscited by 1
  8. 2022Gui at MixMT 2022 : English-Hinglish: An MT approach for translation of code mixed datacited by 1
  9. 2024Who Speaks Matters: Analysing the Influence of the Speaker's Ethnicity on Hate Classificationcited by 1
  10. 2025Sample-Efficient Language Model for Hinglish Conversational AIcited by 1
  11. 2026PingPong: A Natural Benchmark for Multi-Turn Code-Switching Dialoguescited by 1
  12. 2022PreCogIIITH at HinglishEval : Leveraging Code-Mixing Metrics & Language Model Embeddings To Estimate Code-Mix Qualitycited by 0
  13. 2022JU_NLP at HinglishEval: Quality Evaluation of the Low-Resource Code-Mixed Hinglish Textcited by 0
  14. 2022BITS Pilani at HinglishEval: Quality Evaluation for Code-Mixed Hinglish Text Using Transformerscited by 0
  15. 2022The University of Edinburgh's Submission to the WMT22 Code-Mixing Shared Task (MixMT)cited by 0
  16. 2022Domain Curricula for Code-Switched MT at MixMT 2022cited by 0