Repository logo
  • English
  • العربية
  • বাংলা
  • Català
  • Čeština
  • Deutsch
  • Ελληνικά
  • Español
  • Suomi
  • Français
  • Gàidhlig
  • हिंदी
  • Magyar
  • Italiano
  • Қазақ
  • Latviešu
  • Nederlands
  • Polski
  • Português
  • Português do Brasil
  • Srpski (lat)
  • Српски
  • Svenska
  • Türkçe
  • Yкраї́нська
  • Tiếng Việt
Log In
New user? Click here to register.Have you forgotten your password?
  1. Home
  2. Scholalry Output
  3. Publications
  4. MIPE: A Metric Independent Pipeline for Effective Code-Mixed NLG Evaluation
 
  • Details

MIPE: A Metric Independent Pipeline for Effective Code-Mixed NLG Evaluation

Source
Eval4nlp 2021 Evaluation and Comparison of Nlp Systems Proceedings of the 2nd Workshop
Date Issued
2021-01-01
Author(s)
Garg, Ayush
Kagi, Sammed S.
Srivastava, Vivek
Singh, Mayank  
DOI
10.26615/978-954-452-056-4_013
Abstract
Code-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.
Publication link
https://doi.org/10.26615/978-954-452-056-4_013
URI
https://d8.irins.org/handle/IITG2025/26388
IITGN Knowledge Repository Developed and Managed by Library

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science

  • Privacy policy
  • End User Agreement
  • Send Feedback
Repository logo COAR Notify