no code implementations • EMNLP (WNUT) 2020 • Ankit Kumar, Piyush Makhija, Anuj Gupta
Owing to the phenomenal success of BERT on various NLP tasks and benchmark datasets, industry practitioners are actively experimenting with fine-tuning BERT to build NLP applications for solving industry use cases.
no code implementations • 4 Mar 2024 • Ramanathan Vishnampet, Rajesh Shenoy, Jianhui Chen, Anuj Gupta
We have found this technique to be a model-agnostic, cheap and effective way to monitor complex data pipelines in production and have deployed a system for continuously analyzing the global feature importance distribution of continuously trained models.
no code implementations • 15 Jan 2024 • Anuj Gupta, Yasser Atef, Anna Mills, Maha Bali
This study explores how discussing metaphors for AI can help build awareness of the frames that shape our understanding of AI systems, particularly large language models (LLMs) like ChatGPT.
no code implementations • 7 Oct 2021 • Kartikay Bagla, Ankit Kumar, Shivam Gupta, Anuj Gupta
However, for most datasets that are used by practitioners to build industrial NLP applications, it is hard to guarantee the presence of any noise in the data.
no code implementations • COLING 2020 • Piyush Makhija, Ankit Kumar, Anuj Gupta
We present hinglishNorm - a human annotated corpus of Hindi-English code-mixed sentences for text normalization task.
2 code implementations • 18 Oct 2020 • Piyush Makhija, Ankit Kumar, Anuj Gupta
We present hinglishNorm -- a human annotated corpus of Hindi-English code-mixed sentences for text normalization task.
no code implementations • 29 Mar 2020 • Ankit Kumar, Piyush Makhija, Anuj Gupta
Owing to the phenomenal success of BERT on various NLP tasks and benchmark datasets, industry practitioners are actively experimenting with fine-tuning BERT to build NLP applications for solving industry use cases.