Garg, AyushKagi, Sammed ShantinathSrivastava, VivekSingh, MayankGarg, AyushAyushGargKagi, Sammed ShantinathSammed ShantinathKagiSrivastava, VivekVivekSrivastavaSingh, MayankMayankSingh2025-08-282025-08-282021-07-01http://arxiv.org/abs/2107.11534http://repository.iitgn.ac.in/handle/IITG2025/19817Code-mixing is a phenomenon of mixing words and phrases from two or more languages in a single utterance of speech and text. Due to the high linguistic diversity, code-mixing presents several challenges in evaluating standard natural language generation (NLG) tasks. Various widely popular metrics perform poorly with the code-mixed NLG tasks. To address this challenge, we present a metric independent evaluation pipeline MIPE that significantly improves the correlation between evaluation metrics and human judgments on the generated code-mixed text. As a use case, we demonstrate the performance of MIPE on the machine-generated Hinglish (code-mixing of Hindi and English languages) sentences from the HinGE corpus. We can extend the proposed evaluation strategy to other code-mixed language pairs, NLG tasks, and evaluation metrics with minimal to no effort.en-USe-Printe-Print123456789/435