Sample-Efficient Language Model for Hinglish Conversational AI
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912349342924800 |
|---|---|
| author | Singh, Sakshi Prakash, Abhinav Shah, Aakriti Sachdeva, Chaitanya Dumpala, Sanjana |
| author_facet | Singh, Sakshi Prakash, Abhinav Shah, Aakriti Sachdeva, Chaitanya Dumpala, Sanjana |
| contents | This paper presents our process for developing a sample-efficient language model for a conversational Hinglish chatbot. Hinglish, a code-mixed language that combines Hindi and English, presents a unique computational challenge due to inconsistent spelling, lack of standardization, and limited quality of conversational data. This work evaluates multiple pre-trained cross-lingual language models, including Gemma3-4B and Qwen2.5-7B, and employs fine-tuning techniques to improve performance on Hinglish conversational tasks. The proposed approach integrates synthetically generated dialogues with insights from existing Hinglish datasets to address data scarcity. Experimental results demonstrate that models with fewer parameters, when appropriately fine-tuned on high-quality code-mixed data, can achieve competitive performance for Hinglish conversation generation while maintaining computational efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_19070 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sample-Efficient Language Model for Hinglish Conversational AI Singh, Sakshi Prakash, Abhinav Shah, Aakriti Sachdeva, Chaitanya Dumpala, Sanjana Computation and Language I.2.7; I.2.6; H.5.2 This paper presents our process for developing a sample-efficient language model for a conversational Hinglish chatbot. Hinglish, a code-mixed language that combines Hindi and English, presents a unique computational challenge due to inconsistent spelling, lack of standardization, and limited quality of conversational data. This work evaluates multiple pre-trained cross-lingual language models, including Gemma3-4B and Qwen2.5-7B, and employs fine-tuning techniques to improve performance on Hinglish conversational tasks. The proposed approach integrates synthetically generated dialogues with insights from existing Hinglish datasets to address data scarcity. Experimental results demonstrate that models with fewer parameters, when appropriately fine-tuned on high-quality code-mixed data, can achieve competitive performance for Hinglish conversation generation while maintaining computational efficiency. |
| title | Sample-Efficient Language Model for Hinglish Conversational AI |
| topic | Computation and Language I.2.7; I.2.6; H.5.2 |
| url | https://arxiv.org/abs/2504.19070 |