Code-switched Language Models Using Dual RNNs and Same-Source Pretraining
Not on the map. Why?
Abstract (arXiv)
This work focuses on building language models (LMs) for code-switched text. We propose two techniques that significantly improve these LMs: 1) A novel recurrent neural network unit with dual components that focus on each language in the code-switched text separately 2) Pretraining the LM using synthetic text from a generative model estimated using the training data. We demonstrate the effectiveness of our proposed techniques by reporting perplexities on a Mandarin-English task and derive significant reductions in perplexity.
Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 Sep 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 3; 2023: 4; 2024: 1; 2025: 3; 2026: 1.
16 papers.
Sort:
- 2022The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challengescited by 35
- 2021From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Textcited by 29
- 2021Can You Traducir This? Machine Translation for Code-Switched Inputcited by 21
- 2021Exploring Text-to-Text Transformers for English to Hinglish Machine Translation with Synthetic Code-Mixingcited by 16
- 2021Investigating Code-Mixed Modern Standard Arabic-Egyptian to English Machine Translationcited by 10
- 2022CALCS 2021 Shared Task: Machine Translation for Code-Switched Datacited by 9
- 2023Contextual Label Projection for Cross-Lingual Structured Predictioncited by 9
- 2023Code-Switched Text Synthesis in Unseen Language Pairscited by 7
- 2024SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparednesscited by 7
- 2023Persona-aware Generative Model for Code-mixed Languagecited by 3
- 2025Conditioning LLMs to Generate Code-Switched Textcited by 3
- 2025Low-resource Machine Translation for Code-switched Kazakh-Russian Language Paircited by 3
4 more
- 2022SIT at MixMT 2022: Fluent Translation Built on Giant Pre-trained Modelscited by 1
- 2023The Effect of Alignment Objectives on Code-Switching Translationcited by 1
- 2025Building English ASR model with regional language supportcited by 0
- 2026NLP Privacy Risk Identification in Social Media (NLP-PRISM): A Surveycited by 0
- 2026NLP Privacy Risk Identification in Social Media (NLP-PRISM): A Survey26 Jan 2026
- 2025Low-resource Machine Translation for Code-switched Kazakh-Russian Language Pair25 Mar 2025
- 2025Building English ASR model with regional language support10 Mar 2025
- 2025Conditioning LLMs to Generate Code-Switched Text18 Feb 2025
- 2024SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparedness24 Oct 2024
- 2023Contextual Label Projection for Cross-Lingual Structured Prediction16 Sep 2023
- 2023The Effect of Alignment Objectives on Code-Switching Translation10 Sep 2023
- 2023Persona-aware Generative Model for Code-mixed Language6 Sep 2023
- 2023Code-Switched Text Synthesis in Unseen Language Pairs26 May 2023
- 2022The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges19 Dec 2022
- 2022SIT at MixMT 2022: Fluent Translation Built on Giant Pre-trained Models21 Oct 2022
- 2022CALCS 2021 Shared Task: Machine Translation for Code-Switched Data19 Feb 2022
4 more
- 2021From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text14 Jul 2021
- 2021Investigating Code-Mixed Modern Standard Arabic-Egyptian to English Machine Translation28 May 2021
- 2021Exploring Text-to-Text Transformers for English to Hinglish Machine Translation with Synthetic Code-Mixing18 May 2021
- 2021Can You Traducir This? Machine Translation for Code-Switched Input11 May 2021
- 2022The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challengescited by 35
- 2021From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Textcited by 29
- 2021Can You Traducir This? Machine Translation for Code-Switched Inputcited by 21
- 2021Exploring Text-to-Text Transformers for English to Hinglish Machine Translation with Synthetic Code-Mixingcited by 16
- 2021Investigating Code-Mixed Modern Standard Arabic-Egyptian to English Machine Translationcited by 10
- 2022CALCS 2021 Shared Task: Machine Translation for Code-Switched Datacited by 9
- 2023Contextual Label Projection for Cross-Lingual Structured Predictioncited by 9
- 2023Code-Switched Text Synthesis in Unseen Language Pairscited by 7
- 2024SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparednesscited by 7
- 2023Persona-aware Generative Model for Code-mixed Languagecited by 3
- 2025Conditioning LLMs to Generate Code-Switched Textcited by 3
- 2025Low-resource Machine Translation for Code-switched Kazakh-Russian Language Paircited by 3
12 most cited of 16 All 16 (JSON)
- 2026NLP Privacy Risk Identification in Social Media (NLP-PRISM): A Survey26 Jan 2026
- 2025Low-resource Machine Translation for Code-switched Kazakh-Russian Language Pair25 Mar 2025
- 2025Building English ASR model with regional language support10 Mar 2025
- 2025Conditioning LLMs to Generate Code-Switched Text18 Feb 2025
- 2024SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparedness24 Oct 2024
- 2023Contextual Label Projection for Cross-Lingual Structured Prediction16 Sep 2023
- 2023The Effect of Alignment Objectives on Code-Switching Translation10 Sep 2023
- 2023Persona-aware Generative Model for Code-mixed Language6 Sep 2023
- 2023Code-Switched Text Synthesis in Unseen Language Pairs26 May 2023
- 2022The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges19 Dec 2022
- 2022SIT at MixMT 2022: Fluent Translation Built on Giant Pre-trained Models21 Oct 2022
- 2022CALCS 2021 Shared Task: Machine Translation for Code-Switched Data19 Feb 2022
12 newest of 16 All 16 (JSON)